Comparison Claims ledger.

/compare/claims-ledger Checked 2026-11-15

Every claim about another vendor on the three comparison pages: 335 claims, each with the vendor’s own words and the page they are on. Every page was checked on 2026-11-15. A “not published” row means the page that was read does not say. Every grid cell on the comparison pages is in this ledger.

335 vendor claims // 3 comparison pages // Every source dated // 2026-11-15 last checked
[ 02 // how to read it ]
[ 02 ]

The vendor’s own words.
Next to every claim.

The quotes are the exact words saved from each page. A script copies them from the research file, so none is retyped. Markdown marks are removed from quotes that come from a Markdown page.

[ 03 // vendor mcp servers ]
[ 03 ]

StackJack and vendor-native MCP servers

Sources, each checked 2026-11-15

  1. 1Syncro. https://www.syncrosecure.com/platform/mcp-server/
  2. 2Syncro. https://syncrosecure.com/blog/building-syncro-mcp-server/
  3. 3SuperOps. https://support.superops.com/en/articles/16782631-superops-mcp-for-msps
  4. 4HaloPSA. https://www.usehalo.com/guides/2597
  5. 5HaloPSA. https://www.usehalo.com/product-updates/whats-new-in-halopsa-q3-2025
  6. 6HaloPSA. https://www.usehalo.com/guides/2875
  7. 7Thread. https://docs.getthread.com/super-magic/thread-mcp-server-developer-guide.md
  8. 8Thread. https://docs.getthread.com/super-magic/control-who-can-connect-ai-apps-to-thread-mcp.md
  9. 9Thread. https://docs.getthread.com/super-magic/issue-mcp-automation-keys-for-team-members.md
  10. 10NinjaOne. https://www.ninjaone.com/press/katana-ai-and-mcp/
  11. 11NinjaOne. https://www.ninjaone.com/katana-ai/
  12. 12N-able. https://developer.n-able.com/gql/docs/mcp
  13. 13N-able. https://www.n-able.com/press/press-releases/n-able-makes-uem-ai-native-with-mcp-server-launch
  14. 14N-able. https://documentation.n-able.com/N-central/Release_Notes/GA/Content/N-central_2026.2_Release_Notes.htm
  15. 15Huntress. https://www.huntress.com/blog/huntress-mcp-server
  16. 16Huntress. https://support.huntress.io/hc/en-us/articles/50846554117395-Connecting-to-the-Huntress-MCP-Server
  17. 17Huntress. https://feedback.huntress.com/changelog/huntress-mcp-server-is-now-available
  18. 18MSP360. https://www.msp360.com/resources/blog/mcp-server-for-backup-management/
  19. 19MSP360. https://help.mspbackups.com/ai-integration-mcp/connect-claude
  20. 20MSP360. https://www.msp360.com/msp-software/mcp-server/
  21. 21MSP360. https://help.mspbackups.com/ai-integration-mcp/manage-mcp
  22. 22Hudu. https://www.hudu.com/blog/release-update-2.42.0
  23. 23Hudu. https://www.hudu.com/product/features/mcp
  24. 24Liongard. https://docs.liongard.com/docs/model-context-protocol-mcp-server
  25. 25Liongard. https://www.liongard.com/media-press/liongard-platform-expansion-mcp-asset-intelligence/
  26. 26Liongard. https://docs.liongard.com/docs/liongard-mcp-faqs
  27. 27Liongard. https://innovation.liongard.com/
  28. 28Liongard. https://docs.liongard.com/docs/liongards-app-activity-logging
  29. 29Pax8. https://devx.pax8.com/docs/mcp-server

Grid cells

VendorRowThe cell saysMarkThe vendor’s wordsSource
SyncroConnects your AI toSyncrovalueconnects your live Syncro data to the AI assistants you're already using1
SyncroStatus on its own pageGenerally available since 2026-08-11valueThe Syncro MCP Server is generally available August 11, 2026, included in every Syncro plan.1
SyncroPrice of the MCP serverIncluded in every Syncro plan, with no added feecheckit's free to connect in every Syncro plan. No added fees or costs.1
SyncroAI clients it namesClaude, ChatGPT, Microsoft Copilot, Cursorvalueincluding Claude, ChatGPT, Microsoft Copilot, and Cursor1
SyncroSign-in and accessOAuth 2.1. Credentials are scoped, time-limited and can be revokedvalueAccess runs on OAuth 2.1 with scoped, time-limited credentials you can revoke at any time.1
SyncroWrite actionsUnder the approval rules you set in your AI toolcheckAnything that creates or changes a record follows the approval conventions you set in your AI tool1
SyncroAudit logNot published as a log. Its blog says each action is attributed to a personnot publishedactivity logging so every action can be attributed to the person who took it2, 1
SuperOpsConnects your AI toSuperOpsvalueSuperOps MCP connects your AI assistant directly to your SuperOps MSP workspace.3
SuperOpsStatus on its own pageNo stage or date on the articlenot publishedUpdated over 2 weeks ago3
SuperOpsPrice of the MCP serverNot publishednot publishedNo price wording on any page read (searched price, pricing, free, cost, no additional).3
SuperOpsAI clients it namesClaude, ChatGPT, a custom LLMvalueAn MCP-compatible AI client (Claude, ChatGPT, or a custom LLM)3
SuperOpsSign-in and accessA client ID and a secret key. Each module is read only, read and write, or offvalueSecret Key: the credential your AI client uses alongside the Client ID to authenticate with SuperOps over MCP.; Read only: the AI can retrieve data3
SuperOpsWrite actionsFor Tickets and Assets. Every other module is read-onlycheckRead & Write is available for Tickets and Assets only. All other modules are read-only.3
SuperOpsAudit logNot publishednot publishedNo audit wording on the page read.3
HaloPSAConnects your AI toHaloPSAvalueallows AI assistants such as OpenAI to connect and dynamically invoke tools in the Halo API4
HaloPSAStatus on its own pageNo stage on its MCP guide. Its Q3 2025 notes and its chat guides say betavalueAlthough still in beta, MCP is intended to become the primary framework for agentic AI in Halo; + HaloMCP (Beta)5, 6, 4
HaloPSAPrice of the MCP serverNot publishednot publishedNo price wording on any page read (searched price, pricing, free, cost, no additional).4
HaloPSAAI clients it namesOpenAI, in the guide we readvalueallows AI assistants such as OpenAI to connect4
HaloPSASign-in and accessA bearer token from a Halo API applicationvalueensure the application used to generate the bearer token is granted only the permissions required by the available tools4
HaloPSAWrite actionsAdd a note to a ticket, log time, run a runbookcheckAdd Note to Ticket - Allows you to add a private note to a ticket on behalf of the agent, allowing agents to update tickets.; Log Time - Logs a quick time entry for the agent.; Execute a Runbook - Executes a runbook of choice.4
HaloPSAAudit logA setting turns on MCP request loggingcheckit is advisable to enable the logs for this by navigating to Configuration > AI > Halo MCP Server; Enable MCP request logging6
ThreadConnects your AI toThread’s service-desk toolsvalueConnect Claude Desktop, ChatGPT, Cursor, or any MCP client to Thread's service-desk API via OAuth 2.1 to search tickets, manage contacts, and run write actions.7
ThreadStatus on its own pageGenerally available to all partnersvalueAvailability: generally available to all partners.7
ThreadPrice of the MCP serverOpen to all partners. Write tools need an Agentic planvalueAvailability: generally available to all partners.; Write and integration tools appear only on Agentic plans.7
ThreadAI clients it namesClaude Desktop, ChatGPT, Cursor, or any MCP clientvalueConnect Claude Desktop, ChatGPT, Cursor, or any MCP client to Thread's service-desk API via OAuth 2.1 to search tickets, manage contacts, and run write actions.7
ThreadSign-in and accessOAuth 2.1, one member for each connection. Admins choose who may connectvalueWorkspace admins can decide who is allowed to connect at all, see every app that's connected, and cut off any app with one click.; Connect Claude Desktop, ChatGPT, Cursor, or any MCP client to Thread's service-desk API via OAuth 2.1 to search tickets, manage contacts, and run write actions.8, 9, 7
ThreadWrite actionsOn Agentic plans. Other plans see read-only toolscheckWrite and integration tools appear only on Agentic plans.; On a non-Agentic plan (no AI Pro), the connection sees only the seven read-only Super Magic tools7
ThreadAudit logEvery tool call is logged under the membercheckevery tool call is logged under the member identity behind the connection.7
NinjaOneConnects your AI toNinjaOnevaluethe NinjaOne MCP server, an agentic orchestration connector that extends the platform's governed access to the AI tools teams already use10
NinjaOneStatus on its own pageAnnounced 2026-10-13valueOct 13, 202610
NinjaOnePrice of the MCP serverNot publishednot publishedNo price wording on any page read (searched price, pricing, free, cost, no additional).10
NinjaOneAI clients it namesNone namednot publishedexternal AI agents; AI tools10
NinjaOneSign-in and accessThe same role-based permissions as the platformvaluegoverned by the same role-based permissions IT teams already manage10
NinjaOneWrite actionsIt can take action in the NinjaOne platformcheckIt lets external AI agents interact with NinjaOne data and take action directly in the NinjaOne platform.10
NinjaOneAudit logNot published for MCPnot publishedThe audit wording on its page is about Katana AI, not about the MCP server.11
N-ableConnects your AI toN-central and N-sight RMMvalueit provides AI assistants with real-time access to N-central, N-sight RMM, and other supported data sources12
N-ableStatus on its own pageAnnounced 2026-04-13. Its docs say active development. Its release notes say public previewvalueN-able MCP is in active development; April 13th, 2026; MCP Servers are available in public preview.12, 13, 14
N-ablePrice of the MCP serverNot publishednot publishedNo price wording on any page read (searched price, pricing, free, cost, no additional).12, 13
N-ableAI clients it namesClaude Desktop, Claude Code, Gemini CLI, Copilot in VS Code, Copilot StudiovalueGemini CLI Google Workspace/CLI flow using httpUrl and token header.; Copilot Studio Step-by-step setup for adding N-able MCP inside a Copilot Studio agent12
N-ableSign-in and accessAn API token. It inherits the permissions of the N-able SSO user who made itvalueAPI tokens inherit permissions from the N-able SSO user who created them12
N-ableWrite actionsCan run scripts and modify devices. A read-only endpoint is the suggested startcheckCan query data, execute scripts, and modify devices.; Recommended starting point for most use cases.12
N-ableAudit logNot published for MCP. Its release notes say an AI audit log comes laternot publishedAI Audit Log, AI Conversation Log and AI Usage Dashboard will be implemented at a later stage and details will be provided.14
HuntressConnects your AI toHuntressvalueThe Huntress MCP Server provides read-only access to your account data, including agents, organizations, incident reports, signals, escalations, remediations, invoices, reports, and external recon.15
HuntressStatus on its own pageIts own pages give three dates: 2026-04-22, 2026-04-27 and 2026-08-07valueApril 22, 2026; August 7, 202616, 17, 15
HuntressPrice of the MCP serverNot publishednot publishedNo price wording on any page read (searched price, pricing, free, cost, no additional).15, 16
HuntressAI clients it namesClaude Desktop, Claude Code, ChatGPT. Its support article names Claude and OpenAI Codexvaluean MCP-compatible AI client like Claude Desktop, Claude Code, or ChatGPT; connects AI assistants like Claude and OpenAI Codex directly to your Huntress account data.15, 16
HuntressSign-in and accessOAuth, or Base64-encoded credentialsvalueTwo authentication methods are supported: OAuth (recommended) and Base64-encoded credentials.15
HuntressWrite actionsRead-onlyXthe AI can surface your data, but it can't make changes to your account15
HuntressAudit logNot publishednot publishedNo audit wording on the pages read.15, 16
MSP360Connects your AI toMSP360 Managed BackupvalueIt connects your MSP360 Managed Backup account to Claude and ChatGPT18
MSP360Status on its own pageAnnounced 2026-11-03, for all its MSP backup users. Its help article says results are not for productionvalueNovember 3, 2026; MSP360 MCP Server is available to all MSP backup Software users.; Results provided by the MCP server should be reviewed and verified before use and are not recommended for production environments.18, 19
MSP360Price of the MCP serverNothing more to buy. No paid Claude or ChatGPT plan is neededcheckThere’s nothing to buy on either side: you don’t need a paid Claude or ChatGPT plan.; No paid ChatGPT or Claude subscription required.18, 20
MSP360AI clients it namesClaude (desktop and mobile apps) and ChatGPTvalueIt works with Claude (desktop and mobile apps) and ChatGPT.18, 20
MSP360Sign-in and accessAn MSP360 Managed Backup account. The provider sets access to Disabled, Read-only or FullvalueAdd the MSP360 MCP Server to Claude or ChatGPT as a custom connector and sign in with your MSP360 Managed Backup account.; Set MCP access account-wide to Disabled, Read-only, or Full access18, 20
MSP360Write actionsOn Full access. Read-only mode blocks every changecheckIt reads data and it makes changes, within what your account is allowed to do.; cannot create, modify, start, or delete anything.18, 20
MSP360Audit logNot publishednot publishedSearched the blog, product page, manage-MCP article and connect-Claude article.18, 20, 21, 19
HuduConnects your AI toHuduvalueHudu v2.42.0 introduces the Hudu MCP Server22
HuduStatus on its own pageIn release 2.42.0, 2026-05-14value5/14/2026; Hudu v2.42.0 introduces the Hudu MCP Server22
HuduPrice of the MCP serverIncluded with a Hudu subscription, at no added costcheckThe Hudu MCP Server is included with your existing Hudu subscription at no additional cost.23
HuduAI clients it namesClaude, ChatGPT, Cursor, Copilot StudiovalueWorks with Claude, ChatGPT, Cursor, and Copilot Studio23
HuduSign-in and accessOAuth-basedvalueEvery action through the Hudu MCP Server runs through OAuth-based authentication23
HuduWrite actionsEdit documents, update asset records, run process checklists, apply compliance labelscheckdraft or edit documentation, look up and update asset records, create and run process checklists (onboarding, offboarding, maintenance), apply compliance labels23
HuduAudit logAI actions appear in Hudu’s activity logscheckArticle edits, asset changes, and other AI-initiated actions appear in Hudu's activity logs the same way manual changes do23
LiongardConnects your AI toLiongardvalueLiongard partners can enable direct, secure access to Liongard's Model Context Protocol (MCP) server24
LiongardStatus on its own pageAnnounced 2026-04-16. Its docs page gives no stagevalueApril 16, 2026; The new MCP server opens secure, API-driven access to LiongardIQ asset intelligence25, 24
LiongardPrice of the MCP serverNo amount. Its own pages differ: the docs name an MCP subscription, and another page says MCP is includedvalueAn active LiongardIQ and Liongard MCP subscription; These tokens incur an additional cost and provide more limited, controlled access than the global token.; MCP is now included for all Liongard partners24, 26, 27
LiongardAI clients it namesClaude, Cursor, n8n, VS Code, OpenAI ChatKit, Zed, Copilot StudiovalueClaude (Chat, Cowork, Code) Cursor n8n VS Code OpenAI ChatKit Zed Microsoft Copilot Studio24
LiongardSign-in and accessOAuth 2.0 sign-in, or a bearer tokenvalueOAuth 2.0 sign-in: Connect your MCP client with a browser sign-in and a one-click approval using your existing Liongard login.; Bearer Tokens: Generate authentication tokens through the Admin console.24
LiongardWrite actionsNot published. Its tool list holds lookupsnot publishedenables conversational, chat-driven interaction with managed environments for real-time insight and action24
LiongardAudit logNot published for MCPnot publishedLogs AI-related operations and user management actions to provide full visibility into administrative and automation activity.28
Pax8Connects your AI toPax8valueenabling AI assistants like Claude, Copilot, and Cursor to access your Pax8 data and perform actions on your behalf29
Pax8Status on its own pageNo stage in the docsnot publishedUpdated 6 months ago29
Pax8Price of the MCP serverNot publishednot publishedNo price wording on any page read (searched price, pricing, free, cost, no additional).29
Pax8AI clients it namesCursor, Claude, Copilot, VS Code, n8nvalueCursor Claude Copilot VSCode n8n (OAuth 2.0 only)29
Pax8Sign-in and accessOAuth 2.0 or a legacy token. You control which API endpoints are accessiblevalueChoose your preferred connection method (OAuth 2.0 or Pax8 token (legacy)); You maintain control over which API endpoints are accessible and can revoke access at any time.29
Pax8Write actionsIt can perform actions on your behalfcheckAsk questions and initiate actions using simple, intuitive prompts.; enabling AI assistants like Claude, Copilot, and Cursor to access your Pax8 data and perform actions on your behalf29
Pax8Audit logAll actions are logged and can be auditedcheckAll actions performed through the MCP Server are fully logged and auditable.29

Text outside the grid on this page repeats grid cells and carries the same source numbers.

[ 04 // gateways and platforms ]
[ 04 ]

StackJack next to gateways and platforms

Sources, each checked 2026-11-15

  1. 1WYRE Conduit. https://conduit.wyre.ai/pricing
  2. 2WYRE Conduit. https://conduit.wyre.ai/vendors.json
  3. 3WYRE Conduit. https://conduit.wyre.ai/features
  4. 4WYRE Conduit. https://conduit.wyre.ai/security
  5. 5WYRE Conduit. https://conduit.wyre.ai/docs/getting-started/
  6. 6WYRE Conduit. https://conduit.wyre.ai/docs/guides/workflows/
  7. 7WYRE Conduit. https://conduit.wyre.ai/docs/reference/agents-concepts/
  8. 8Stackyapper. https://stackyapper.dev/
  9. 9Stackyapper. https://stackyapper.dev/how-it-works
  10. 10Stackyapper. https://stackyapper.dev/pricing
  11. 11Stackyapper. https://stackyapper.dev/apps
  12. 12Stackyapper. https://docs.stackyapper.dev/
  13. 13Stackyapper. https://stackyapper.dev/trust
  14. 14Stackyapper. https://stackyapper.dev/llms.txt
  15. 15Pipedream. https://pipedream.com/docs/connect/mcp.md
  16. 16Pipedream. https://pipedream.com/
  17. 17Pipedream. https://pipedream.com/docs/conduit/cloud.md
  18. 18Pipedream. https://pipedream.com/apps
  19. 19Pipedream. https://pipedream.com/conduit
  20. 20Pipedream. https://pipedream.com/pricing
  21. 21Pipedream. https://pipedream.com/docs/workflows.md
  22. 22Pipedream. https://pipedream.com/docs/connect/components/triggers.md
  23. 23Pipedream. https://pipedream.com/docs/conduit/use/mcp-reference.md
  24. 24Zapier MCP. https://zapier.com/mcp
  25. 25Zapier MCP. https://docs.zapier.com/mcp/manage/security.md
  26. 26Zapier MCP. https://docs.zapier.com/mcp/get-started/build-a-workflow.md
  27. 27Zapier MCP. https://zapier.com/pricing
  28. 28Zapier MCP. https://docs.zapier.com/mcp/overview/how-connections-work.md
  29. 29Zapier MCP. https://docs.zapier.com/mcp/get-started/rollout/overview.md
  30. 30Zapier MCP. https://zapier.com/enterprise
  31. 31Zapier MCP. https://docs.zapier.com/mcp/embed/getting-started.md
  32. 32Composio. https://composio.dev/pricing
  33. 33Composio. https://composio.dev/mcp-gateway
  34. 34Composio. https://composio.dev/toolkits/halopsa
  35. 35Composio. https://composio.dev/pricing/platform
  36. 36Composio. https://docs.composio.dev/llms.txt
  37. 37Composio. https://docs.composio.dev/docs/triggers.md
  38. 38Composio. https://docs.composio.dev/docs/governance/approvals.md
  39. 39n8n. https://n8n.io/
  40. 40n8n. https://n8n.io/pricing/
  41. 41n8n. https://n8n.io/mcp/
  42. 42n8n. https://n8n.io/integrations/halopsa/
  43. 43n8n. https://n8n.io/integrations/
  44. 44n8n. https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-langchain.mcptrigger/
  45. 45n8n. https://n8n.io/legal/security/
  46. 46n8n. https://n8n.io/enterprise/
  47. 47Cloudflare. https://developers.cloudflare.com/changelog/post/2026-09-24-mcp-portals-ga/
  48. 48Cloudflare. https://developers.cloudflare.com/cloudflare-one/access-controls/ai-controls/mcp-portals/
  49. 49Cloudflare. https://blog.cloudflare.com/mcp-portal-writeguard-private-beta/
  50. 50Cloudflare. https://www.cloudflare.com/plans/zero-trust-services/
  51. 51Cloudflare. https://developers.cloudflare.com/cloudflare-one/traffic-controls/tiered-policies/tenant-api/
  52. 52Cloudflare. https://www.cloudflare.com/trust-hub/compliance-resources/
  53. 53Rewst. https://rewst.io/resources/news/rewst-unveils-suite-of-ai-capabilities-from-workflow-creation-using-natural-language-to-an-mcp-server-connecting-ai-agents-with-automations
  54. 54Rewst. https://rewst.io/platform/fabric
  55. 55Rewst. https://rewst.io/platform/integrations
  56. 56Rewst. https://rewst.io/pricing
  57. 57Rewst. https://rewst.io/
  58. 58Rewst. https://rewst.io/trust-center
  59. 59Rewst. https://rewst.io/platform/workflow-builder
  60. 60Hatz AI. https://www.hatz.ai/
  61. 61Hatz AI. https://docs.hatz.ai/en/articles/13722060-halo-psa-integration
  62. 62Hatz AI. https://docs.hatz.ai/en/articles/13727834-pax8-integration
  63. 63Hatz AI. https://docs.hatz.ai/en/articles/12430282-list-of-integrations
  64. 64Hatz AI. https://www.hatz.ai/partners
  65. 65Hatz AI. https://www.hatz.ai/credit-usage-faq
  66. 66Hatz AI. https://docs.hatz.ai/en/articles/14115976-custom-mcp-servers
  67. 67Hatz AI. https://docs.hatz.ai/en/articles/15394302-autotask-mcp-integration
  68. 68Hatz AI. https://www.hatz.ai/msps
  69. 69Hatz AI. https://hatz-ai.canny.io/changelog
  70. 70Pax8 (8os and 8bot). https://www.pax8.com/en-us/8os-agentic-workforce-operating-system/
  71. 71Pax8 (8os and 8bot). https://www.pax8.com/en-us/8bot-managed-ai-coworker/
  72. 72Pax8 (8os and 8bot). https://www.pax8.com/blog/introducing-8os-and-8bot/
  73. 73Kaseya. https://www.kaseya.com/press-release/kaseya-previews-next-evolution-of-kaseya-intelligence-at-connect-europe-2026/
  74. 74Kaseya. https://www.kaseya.com/platform/
  75. 75Kaseya. https://webinar.kaseya.com/kaseya-innovations-for-the-microsoft-ecosystem
  76. 76Kaseya. https://www.kaseya.com/platform/kaseya-365/
  77. 77Kaseya. https://www.kaseya.com/platform/intelligence/
  78. 78Kaseya. https://www.kaseya.com/trust-center/information-security/
  79. 79Thread. https://docs.getthread.com/super-magic/add-external-tools-to-super-magic-with-connectors-super-mcp.md
  80. 80Thread. https://docs.getthread.com/super-magic/thread-mcp-server-developer-guide.md
  81. 81Thread. https://docs.getthread.com/llms.txt
  82. 82Thread. https://www.getthread.com/thread-pricing
  83. 83Thread. https://docs.getthread.com/super-magic/control-who-can-connect-ai-apps-to-thread-mcp.md
  84. 84Thread. https://docs.getthread.com/super-magic/issue-mcp-automation-keys-for-team-members.md
  85. 85Thread. https://docs.getthread.com/security-billing/soc-2-and-compliance-status.md
  86. 86Thread. https://trust.getthread.com/
  87. 87Thread. https://docs.getthread.com/super-magic/faq.md
  88. 88Thread. https://docs.getthread.com/super-magic/meet-super-magic-your-ai-assistant-in-the-inbox.md
  89. 89Bifrost (gobifrost.com). https://gobifrost.com/features
  90. 90Bifrost (gobifrost.com). https://gobifrost.com/
  91. 91Bifrost (gobifrost.com). https://github.com/gobifrost/bifrost
  92. 92Bifrost (gobifrost.com). https://gobifrost.com/compare
  93. 93Bifrost (gobifrost.com). https://gobifrost.com/llms-full.txt

Grid cells

VendorRowThe cell saysMarkThe vendor’s wordsSource
WYRE ConduitConnects your AI to230 vendor connectorsvalueAll 230 vendor connectors1, 2
WYRE ConduitStatus on its own pageShipped, as its features page saysvalueEvery card is a real, shipped capability. Nothing aspirational.3
WYRE ConduitMSP tools on its own pagesHaloPSA, ConnectWise PSA, Autotask PSA and NinjaOne are in its vendor listvalueRead from the vendor list that WYRE publishes.2
WYRE ConduitAI clients it namesClaude, ChatGPT, Microsoft Copilot, Cursor, WindsurfvalueConduit works with any MCP-capable AI tool, including Claude, ChatGPT, Microsoft Copilot, Cursor, Windsurf, and more.1
WYRE ConduitPrice on its public page$39 for each seat a month, flatcheck$39 / seat / month1
WYRE ConduitFree planA 14-day trialvalue14-day free trial.1
WYRE ConduitWhat counts against the planSeats, for people and AI agents. The first 2 agent seats are freevalueYour first 2 AI agent seats are free1
WYRE ConduitSign-in and accessOAuth 2.1 with PKCE. A tool allowlist for each role, deny by defaultvalueYour AI clients connect over OAuth 2.1 + PKCE; Decide exactly which vendor tools each role is allowed to invoke. Deny-by-default; grant per-tool, per-role.3
WYRE ConduitWrite actionsNo read or write switch is stated. Its control is the tool allowlistnot publishedThe control it describes is the allowlist in the sign-in row.3
WYRE ConduitAudit logEvery tool call. Tool arguments are recorded only if you turn that oncheckConduit logs every tool call your team makes: who ran what, against which vendor, when.; optionally record tool arguments and result summaries. Off by default3
WYRE ConduitA setup for each customerCustomers are kept apart, each with its own users, vendors and audit logcheckRun an estate of customers and sub-customers, each cleanly isolated with its own users, vendors, and audit log.3
WYRE ConduitSOC 2Not certified. Its page says it is preparing for SOC 2 Type 2XSOC 2 Not certified Preparing for SOC 2 Type 2.4
WYRE ConduitRuns in your own cloudHosted by WYRE. Its docs mention self-hosted deploymentsvalueConduit is a hosted MCP gateway.; Self-hosted deployments can skip the card field.5
WYRE ConduitWorkflows or agentsWorkflows that Conduit runs for you, and a library of pre-built agentscheckA workflow is a named, versioned definition; that Conduit runs for you, on a schedule or on demand, against your org's already-connected vendor tools; Conduit ships with a library of pre-built agents6, 7
WYRE ConduitTriggersOn a schedule, by hand, or from a webhookcheckA workflow can run on a schedule or when someone starts it, under one runner identity per deployment, with full run history in the console.; A run only knows its trigger's kind (schedule, manual, or webhook)6
WYRE ConduitA person approves an actionAn admin approves a workflow’s tool list before it can run. Approval of each action is not publishedvalueThat list is what an admin reviews and approves before a workflow is allowed to do anything.6
StackyapperConnects your AI to5,200+ app listings for business toolsvalueConnect your business tools to Claude, ChatGPT, and the AI your team already uses.; 5,200+ app listings8
StackyapperStatus on its own pageLive. Each app is marked Certified or Beta. Its MSP features are in previewvalueApps labeled beta are not represented as fully supported.; MSP capabilities are in preview with staged availability9, 10
StackyapperMSP tools on its own pagesConnectWise PSA, NinjaOne, Hudu (Certified). HaloPSA, Autotask PSA (Beta)valueConnectWise PSA PSA Certified; NinjaOne RMM Certified; Hudu Documentation Certified; HaloPSA PSA Beta; Autotask PSA PSA Beta11
StackyapperAI clients it namesClaude, ChatGPT, Codex, Claude Code, Hatz AI, Copilot StudiovaluePoint a supported client at the Stackyapper remote MCP endpoint: Claude, ChatGPT, Codex, Claude Code, or Hatz AI.; Add Stackyapper to Claude, ChatGPT, Codex, Copilot Studio, or another MCP client.9, 12
StackyapperPrice on its public pageStandard: $99 a month. Business: $199 a monthcheckStandard $99 / month; Business $199 / month10
StackyapperFree planNot publishednot publishedNo statement on the page read.10
StackyapperWhat counts against the planThe plan, with no charge for each user, app or call. A customer workspace is $119 a month morevalueUnlimited users, apps, and tool calls.; There is no per-user charge.; Each billable customer workspace $119 per month10
StackyapperSign-in and accessMicrosoft and Google sign-in. SAML and SCIM on Business. Admins allow or block AI clientsvalueBusiness workspaces can use managed SAML and Microsoft Entra SCIM for company sign-in and user lifecycle management.; An unapproved client is stopped during sign-in, before the consent screen, and never receives a grant or token13
StackyapperWrite actionsReads, writes and deletes are treated differently. A risky action can need a confirmationcheckReads, writes, deletes, financial actions, and credential-sensitive actions can receive different treatment.; Actions that require confirmation are bound to the arguments the user reviewed.13
StackyapperAudit logMetadata of each call. Export on BusinesscheckAdministrators can review operational metadata such as the actor, workspace, app, tool, result, client, and duration.; Everything in Standard, plus managed employee access, audit export, and 365 days of activity history.13, 10
StackyapperA setup for each customerCustomer administration and workspace switching, on Business. Its MSP features are in previewnot finalBusiness includes customer administration and workspace switching after MSP or consultant verification.; MSP capabilities are in preview with staged availability10
StackyapperSOC 2Not certified. Its page says the status is preparationXStackyapper is not currently SOC 2 certified, and no examination has been completed.; Current status: Preparation.13
StackyapperRuns in your own cloudHosted. Credentials are kept on its serversvaluehosted MCP access and policy layer; Stackyapper keeps connected-app credentials encrypted on its servers14
StackyapperWorkflows or agentsA policy layer between AI clients and apps. It brings no agent of its ownvalueIt does not replace your AI assistant or require you to adopt one proprietary agent.9
StackyapperTriggersNot publishednot publishedIts pages describe a policy layer, not an automation product.9
StackyapperA person approves an actionA confirmation for higher-risk actionscheckActions that require confirmation are bound to the arguments the user reviewed.13
PipedreamConnects your AI to3,000+ apps, with an MCP server for each appvaluePipedream offers a dedicated MCP (Model Context Protocol) server for all of our 3,000+ integrated apps.15
PipedreamStatus on its own pageConduit is in early access. Its docs list a hosted Conduit Cloudnot finalFor companies · Early access; Conduit Cloud is free for up to 100 users.16, 17
PipedreamMSP tools on its own pagesConnectWise PSA, Autotask PSA and NinjaOne are in its app catalogvalueEvery NinjaOne action is exposed as an MCP tool on Pipedream's remote server. Read from Pipedream’s own app catalog.18
PipedreamAI clients it namesClaude, Cursor, ChatGPT, or any other AI assistantvalueConduit gives you 3,000+ connectors for Claude, Cursor, ChatGPT, or any other AI assistant19, 15
PipedreamPrice on its public pageStartup: $99 a month billed yearly, or $150 monthlycheck$99 per month; $150 per month20
PipedreamFree planFree to build. Hosted MCP servers are free for your own use. Conduit Cloud is free for up to 100 userscheckFree to build. Pay when your integrations go to production.; Anyone can use Pipedream's hosted MCP servers for their own use for free; Conduit Cloud is free for up to 100 users.20, 15, 17
PipedreamWhat counts against the planExternal users, then credits. Each MCP tool call uses creditsvalue100 users included, then $2 per user; 10,000 usage credits included; Running an action, calling a tool through MCP, sending a request through the Connect proxy20
PipedreamSign-in and accessConnect: each user’s credentials are kept apart. Conduit: groups and policies for each toolvalueEach user's credentials are stored securely and isolated from other users; Groups and policies decide who can use which connectors and tools. Every call is authenticated, authorized, and logged.15, 19
PipedreamWrite actionsEach NinjaOne action is an MCP tool, as one examplecheckEvery NinjaOne action is exposed as an MCP tool on Pipedream's remote server.18
PipedreamAudit logConduit: every sign-in, policy change and tool call. Connect: not statedcheckEvery sign-in, policy change, and tool call is recorded.19
PipedreamA setup for each customerNot publishednot publishedNo statement on the page read.19
PipedreamSOC 2Type 2, on every plancheckSOC 2 Type 2 and GDPR Included Included Included20
PipedreamRuns in your own cloudConduit: you can self-host it, or use its managed cloud. Connect: not publishedcheckSelf-host a single Docker image in your own infrastructure, or use the managed cloud.; Self-hosted or in the cloud. Early access is open.; You can also self-host Conduit on your own infrastructure.19, 17
PipedreamWorkflows or agentsPipedream Workflows shuts down on 2027-03-31valuePipedream Workflows and String will shut down on March 31, 2027.21
PipedreamTriggersIn Connect: event triggers that send to a webhook URL or a workflow. A schedule trigger is not publishedcheckTriggers (also called sources) are different from actions; When deploying a source, you can define either a webhook URL or a Pipedream workflow ID to consume those events.; Some app-based triggers poll for new events rather than using webhooks.22
PipedreamA person approves an actionNot published as a Pipedream controlnot publishedIts docs point to the approval setting of the AI client.23
Zapier MCPConnects your AI to9,000+ appsvalueyour agent searches Zapier's 9,000+ apps and 66,000+ triggers and actions24
Zapier MCPStatus on its own pageGenerally available. Next Gen Zaps, which build workflows through MCP, are in early accessvalueZapier MCP is generally available and operates under Zapier's SOC 2 Type II certification.; Next Gen Zaps is in early access by request.25, 26
Zapier MCPMSP tools on its own pagesNone named on its MCP pagenot publishedThe page text names no PSA or RMM product.24
Zapier MCPAI clients it namesClaude, ChatGPT, Cursor, and any other AI clientvalueZapier MCP lets Claude, ChatGPT, Cursor, and any other AI client take real action in the apps that run your business24
Zapier MCPPrice on its public pageProfessional: from $19.99 a month, with yearly billing and 750 taskscheckStarting from $19.99 /month27
Zapier MCPFree planMCP is in every plan. Free has 100 tasks a monthcheckZaps, Tables, and Forms included (100 tasks per month); Zapier MCP is included in every Zapier plan.27, 24
Zapier MCPWhat counts against the planTasks. Each MCP tool call uses twovalueEach tool call uses two tasks from your existing task quota24
Zapier MCPSign-in and accessOAuth from inside the MCP client, or a connection token. Each member signs in as themselvesvalueThe default is OAuth from inside the MCP client.; SOC 2 Type II certified with SAML SSO, OAuth, and connection token auth.; each member still signs in and runs tool calls as themselves28, 25, 29
Zapier MCPWrite actionsIt takes action in your appscheckZapier MCP lets Claude, ChatGPT, Cursor, and any other AI client take real action in the apps that run your business24
Zapier MCPAudit logAgent actions show in the audit log. Its MCP page has an action historycheckEvery agent action taken through Zapier is visible in the audit log.; MCP action History gives you a record of what ran.30, 24
Zapier MCPA setup for each customerIt can be embedded in another product, for that product’s customersvalueYou want to embed Zapier MCP in your own product for your customers.; Embedding Zapier MCP gives your users governed access to 9,000+ apps without leaving your MCP client's interface.29, 31
Zapier MCPSOC 2Type IIcheckSOC 2 Type II certified24
Zapier MCPRuns in your own cloudNot publishednot publishedNo statement on the pages read.27, 30
Zapier MCPWorkflows or agentsZaps, Tables and Forms are included on its Free plancheckZaps, Tables, and Forms included (100 tasks per month)27
Zapier MCPTriggersIn Next Gen Zaps: a schedule, an app event, or on demandnot finalInclude the apps involved, what triggers it (a schedule, an app event, or on-demand only); Next Gen Zaps is in early access by request.26
Zapier MCPA person approves an actionA person approves the build plan of a Next Gen Zap. Approval of each tool call is not publishedvalueReview the plan before continuing.; Once you approve the plan, your agent writes the workflow's TypeScript code26
ComposioConnects your AI to1,700+ apps, on Free and StandardvalueConnect 1,700+ apps to your AI for free.32
ComposioStatus on its own pageNo stage label on its MCP gateway pagenot publishedThe secure MCP gateway for enterprise AI agents33
ComposioMSP tools on its own pagesHaloPSA: 85 tools in its toolkitvalue85 Tools34
ComposioAI clients it namesClaude, Codex, Cursor and more. Its HaloPSA page names Claude, ChatGPT, CursorvalueConnect your apps to Claude, Codex, Cursor and more.; connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with HaloPSA MCP32, 34
ComposioPrice on its public pageStandard: $18 for each seat a monthcheck$18 per seat / month32
ComposioFree plan$0. 10,000 tool calls a month, for up to 3 memberscheck10,000 Each action your AI takes in an app; Members Up to 332
ComposioWhat counts against the planTool calls. Standard adds 10,000 for each seat, and $18 in creditsvalueEvery seat adds 10,000 tool calls and $18 in credits to one pool that your whole workspace shares.32
ComposioSign-in and accessSSO for its gateway. Policies for the org, a team and a uservalueSSO verifies the user before any tool resolves; Org, team, and user policies33
ComposioWrite actionsA team policy can block destructive actionscheckDestructive actions blocked33
ComposioAudit logOn Enterprise. Its Platform tab lists audit logs on every plancheckSCIM provisioning and audit logs; Audit logs A record of who changed what in your organization. Hobby shows the last 30 days.32, 35
ComposioA setup for each customerAn MCP endpoint for each teamvalueEach team gets its own MCP endpoint carrying only the tools it is permitted to use.33
ComposioSOC 2Type II, as stated on its HaloPSA toolkit pagecheckComposio is SOC 2 Type II compliant34
ComposioRuns in your own cloudBring your own cloud, on EnterprisecheckBring your own cloud (BYOC); Choose Enterprise when you need SCIM, SIEM streaming, deployment in your own cloud, or dedicated support.32
ComposioWorkflows or agentsAgents. Its gateway can start background agents from eventscheckBuild and operate agents with authentication, tool discovery, execution, and 1,700+ toolkits.; TRIGGERS Start background agents from events across your connected apps36, 33
ComposioTriggersEvent triggers, sent to your webhook URL. A schedule trigger is not publishedchecksends that event to your app as a structured payload; Composio delivers every event to one destination you control: your webhook URL.37
ComposioA person approves an actionA session setting asks the user before a tool runsnot finalYou can configure the session to require the user's approval before any tool runs; Approvals are experimental.38
n8nConnects your AI toApps through nodes, any API through HTTP, any agent through MCPvalue500+ native integrations. Any API via HTTP. Any agent or coding assistant via MCP.39
n8nStatus on its own pageIts MCP features are on every cloud plan, with no preview label. Its Agents are labelled previewvalueInstance-level MCP Included Included Included; Included on all n8n plans; Agents (preview) Included Included Included40, 41
n8nMSP tools on its own pagesHaloPSA and SyncroMSP have native nodesvalueHaloPSA integrations | Workflow automation with n8n42, 43
n8nAI clients it namesClaude, ChatGPT, Gemini, CursorvalueClaude, ChatGPT, Gemini, or Cursor.41
n8nPrice on its public pageStarter: 20 euros a month, billed yearly, with 2.5K executionscheck20€ /mo, billed annually; 2.5K workflow executions with unlimited steps40
n8nFree planA free self-hosted edition. The cloud has a free trial with no cardcheckStart free trial No credit card required; A standard, self-hosted version of n8n is available on GitHub.40, 39
n8nWhat counts against the planWorkflow executions a month, not steps or usersvalueAll plans include unlimited users and workflows and every integration. Pricing is based on monthly workflow executions, regardless of complexity.40
n8nSign-in and accessIts MCP server trigger can use n8n OAuth2valuen8n User Auth (OAuth2) : available on node version 2 and later.44
n8nWrite actionsIt depends on the workflow tools you expose. Human approval for tool calls is includedvalueHuman approval for tool calls Included Included Included40
n8nAudit logAudit logging is on EnterprisecheckAudit logging Not included Not included Included40
n8nA setup for each customerNot publishednot publishedNo statement on the page read.40
n8nSOC 2Type 2 is listed on its enterprise page. The report is for enterprise customerscheckn8n aligns its security program to SOC 2, a standard framework for security compliance.; Our SOC 2 report is available to enterprise customers.; GDPR SOC 2 Type 245, 46
n8nRuns in your own cloudSelf-host with Docker or on-premcheckDeploy on-prem or with Docker to keep your data in your own environment.; A standard, self-hosted version of n8n is available on GitHub.39, 40
n8nWorkflows or agentsEvery plan has unlimited workflowscheckAll plans include unlimited users and workflows and every integration. Pricing is based on monthly workflow executions, regardless of complexity.40
n8nTriggersAn MCP Server Trigger is on every cloud plancheckMCP Server Trigger Included Included Included40
n8nA person approves an actionHuman approval for tool calls is includedcheckHuman approval for tool calls Included Included Included40
CloudflareConnects your AI toOne endpoint for the MCP servers you approvevalueA portal gives users one endpoint for approved Model Context Protocol (MCP) servers.47
CloudflareStatus on its own pageGenerally available since 2026-09-24. Its finer write controls are in private betavalueMCP server portals are now generally available to all Cloudflare customers.; September 24, 2026; We are now bringing those controls to Cloudflare MCP server portals through a private beta.47, 48, 49
CloudflareMSP tools on its own pagesThe MCP servers you add to the portalvalueA portal gives users one endpoint for approved Model Context Protocol (MCP) servers.47
CloudflareAI clients it namesWorkers AI Playground and other clients that support remote MCP serversvalueusing Workers AI Playground; or other MCP clients that support remote MCP servers48
CloudflarePrice on its public pageNo price of its own. Cloudflare One is $7 for each user a month, pay as you gocheckPay-as-you-go; $7/user/month50
CloudflareFree plan$0, for teams under 50 userscheckFree Plan; Best for teams under 50 users or enterprise proof-of-concept tests.; $0 forever50
CloudflareWhat counts against the planUsersvaluePay-as-you-go; $7/user/month50
CloudflareSign-in and accessAccess policies decide who sees each server. Service tokens for agentsvalueThe MCP server link will only appear in the portal for users who match an Allow policy.; Service token authentication for autonomous agents and machine-to-machine access48, 47
CloudflareWrite actionsAdmins can rename tools and prompts. Finer write controls are in private betavalueAdmins can rename tools and prompts and edit their descriptions at the portal or server level without modifying the upstream MCP server.; WriteGuard is a shared policy, attribution, and auditing layer.; We are now bringing those controls to Cloudflare MCP server portals through a private beta.48, 49
CloudflareAudit logTool, prompt and resource activity. Log export is on Enterprise planscheckCloudflare Access logs tool, prompt, and resource activity.; Export logs with Logpush Availability Only available on Enterprise plans.47, 48
CloudflareA setup for each customerA Tenant API for partner MSPs. Its page does not tie it to MCP portalsvaluewhich allows Cloudflare-partnered managed service providers (MSPs) to set up and manage Cloudflare accounts and services for their customers51
CloudflareSOC 2Type IIcheckSOC 2 Type II; Certification to attest to Security, Confidentiality, and Availability controls in place in accordance to the AICPA Trust Service Criteria.52
CloudflareRuns in your own cloudNot publishednot publishedNo statement on the page read.48
CloudflareWorkflows or agentsNot publishednot publishedA portal is an access and policy layer.48
CloudflareTriggersNot publishednot publishedA portal is an access and policy layer.48
CloudflareA person approves an actionNot publishednot publishedA portal is an access and policy layer.48
RewstConnects your AI toRewst workflows, through its MCP Server. Through Fabric, the tools connected to Rewstvaluegiving agents like ChatGPT, Claude Desktop, and custom copilots secure, structured access to workflows, variables, and metadata; So can another MCP-compatible AI tool your team uses, connected to Rewst.53, 54
RewstStatus on its own pageMCP Server and MCP Trigger announced 2025-06-25. No stage on its Fabric pagevalueDate: 25 June 2025; Rewst also introduced its Model Context Protocol (MCP) Server53, 54
RewstMSP tools on its own pagesHaloPSA, ConnectWise PSA, NinjaOne, Datto RMM, Pax8 and morevalueHaloPSA Enables automation of PSA tasks.; NinjaOne Enables automation of remote monitoring and management.; Datto RMM Enables automation of RMM tasks.; ConnectWise PSA Enables automation of PSA tasks.; Pax8 Enables automation of cloud marketplace operations.55
RewstAI clients it namesChatGPT, Claude Desktop, custom copilotsvaluegiving agents like ChatGPT, Claude Desktop, and custom copilots secure, structured access to workflows, variables, and metadata53
RewstPrice on its public pageNot published. Priced for each client organization, by quotenot publishedWe price per client organization you run on the platform.; Demo the platform and get your quote56
RewstFree planNot publishednot publishedNo statement on the page read.56
RewstWhat counts against the planClient organizations. AI use has an allowance, then your own AI keyvalueSet at 5% of your monthly invoice and included by default.; Connect the API key from your preferred AI provider56
RewstSign-in and accessFabric access is off by default and follows each integration’s permissionsvalueAccess is off by default and limited to the permissions already set for that integration.54
RewstWrite actionsThe Rewst Agent can take action. AI tools can start workflowscheckThe Rewst Agent can take action, too; MCP Trigger: Enables AI tools to initiate Rewst workflows via a lightweight API57, 53
RewstAudit logActions show in the client tenant’s activity log. 30-day execution historycheckEvery action shows up in the client tenant's activity log.; 30-day execution history54, 56
RewstA setup for each customerEach AI connection is scoped to one client tenantcheckEach connection is scoped to one client tenant and can't cross into another.54
RewstSOC 2A SOC 2 report under NDA. The type is not statedcheckAfter signing an NDA, you will be able to access our SOC 2 Report and additional information security program resources.58
RewstRuns in your own cloudNot publishednot publishedNo statement on the page read.56
RewstWorkflows or agentsAn automation platform built for MSPs, with the Rewst AgentcheckOne secure automation platform, built for MSPs, where the work actually runs.57
RewstTriggersManual, on a schedule, or on an event such as a webhookcheckStart an automation manually, on a schedule, or when something happens elsewhere in your stack; a form submission, new ticket, status change, or webhook59
RewstA person approves an actionApproval is a stated step, with a record of who approvedcheckDescribe it. Approve it. Run it.; you can see what ran, when, and who approved it57
Hatz AIConnects your AI toHatz is the AI application. It connects out to MCP servers and integrationsvalueConnect to MCP servers, web search, document analysis, data connectors and integrations.60
Hatz AIStatus on its own pageLive. Its Halo PSA and Pax8 integrations are labelled betavalueBeta: This integration is currently available in Hatz beta.61, 62
Hatz AIMSP tools on its own pagesConnectWise Manage, Autotask, HaloPSAvaluePSA and service management integrations such as ConnectWise Manage, Autotask, HaloPSA63
Hatz AIAI clients it namesHatz is the client. It offers ChatGPT, Claude, Gemini and morevalueAccess ChatGPT, Claude, Gemini and more in one place.60
Hatz AIPrice on its public pageNot publishednot publishedNo statement on the page read.64
Hatz AIFree planNot publishednot publishedNo statement on the page read.64
Hatz AIWhat counts against the planCredits tied to AI use. They reset each monthvalueHatz Credits are units of measure directly tied to AI usage in the Hatz AI platform.; Unused credits from the previous month are not rolled into the next.65
Hatz AISign-in and accessRole-based access. A custom MCP server can use OAuthvalueRole-based access, spending limits and audit logs give you full visibility and control across your entire client base.; OAuth The server requires browser-based OAuth.60, 66
Hatz AIWrite actionsFor Autotask, always behind a confirmation stepcheckalways behind an explicit, reviewable confirmation step67
Hatz AIAudit logAudit logs are named on its home pagecheckRole-based access, spending limits and audit logs give you full visibility and control across your entire client base.60
Hatz AIA setup for each customerA multi-tenant administrative portalcheckour multi-tenant administrative portal64
Hatz AISOC 2Type 2checkSOC 2 Type 2 Independently audited controls60
Hatz AIRuns in your own cloudNot published for Hatz. A custom MCP server is hosted by the customernot publishedHatz AI only supports HTTP-based MCP servers. Customers must host and maintain these servers on their own infrastructure.66
Hatz AIWorkflows or agentsAgents, workflows and automationscheckBuild an Agent Create a custom AI agent; Hatz is purpose-built for MSPs to deploy AI tools, workflows, and agents both internally and to their customers.60, 68
Hatz AITriggersOn a schedule. A webhook trigger is not publishedcheckRun it on a schedule, or click Run with new inputs whenever you need it.69
Hatz AIA person approves an actionSmart mode asks before a risky action. Manual mode asks more oftencheckSmart runs low-risk actions on its own and asks before anything risky. Manual asks before more actions.69
Pax8 (8os and 8bot)Connects your AI to8os: supported AI, through a built-in gateway. 8bot: Microsoft 365valueConnect supported AI through the built-in gateway. Manage usage and budgets by customers.; At beta, 8bot connects to Microsoft 365: Outlook mail, Calendar, Slack, Teams and OneDrive and SharePoint.70, 71
Pax8 (8os and 8bot)Status on its own pageIts pages give two timings: early access now, and access from January 2027not final8bot is currently Early Access.; 8bot access begins in January 2027.70, 71
Pax8 (8os and 8bot)MSP tools on its own pagesNot publishednot publishedNo statement on the pages read.70, 71
Pax8 (8os and 8bot)AI clients it namesNone named for 8os. 8bot is its own AI coworkernot publishedNo statement on the page read.70
Pax8 (8os and 8bot)Price on its public pageNot publishednot publishedNo statement on the pages read.70, 71
Pax8 (8os and 8bot)Free planNot publishednot publishedNo statement on the pages read.70, 71
Pax8 (8os and 8bot)What counts against the plan8bot: a seat is one AI worker for one person. 8os: budgets by customervalueEach seat is one always-on AI worker for one person, running on its own dedicated computer in the cloud.; You can also set budgets and spending limits by customer to help avoid unexpected costs.71, 72
Pax8 (8os and 8bot)Sign-in and access8bot uses the person’s Microsoft work account. Each app connection is approved one by onevalueSign in with the Microsoft work account you already have.; Approve each 8bot app connection individually, starting with read-only access to the work it needs.71, 70
Pax8 (8os and 8bot)Write actionsWith approval. Connections start read-onlycheckConnections start read-only.; every one of those actions still asks for your approval71
Pax8 (8os and 8bot)Audit logNot stated for the MSP. Pax8 support can read the activity recordnot publishedPax8 support can access your AI coworker's activity record to resolve issues71
Pax8 (8os and 8bot)A setup for each customerA multi-tenant provider model, in each client’s contextcheck8os is designed for a multi-tenant provider model, helping MSPs manage agents, access, usage and budgets in each client's context.70
Pax8 (8os and 8bot)SOC 2Not on the 8os and 8bot pages. The Pax8 footer shows ISO 27001not publishedISO 27001 Certified70, 71
Pax8 (8os and 8bot)Runs in your own cloudHosted by Pax8. In the U.S. during the betavalueduring the beta your data is hosted in the U.S.71
Pax8 (8os and 8bot)Workflows or agents8os builds agents. 8bot runs routinescheckBuild agents from scratch. Turn proven workflows into repeatable client services.; Anything you ask for regularly becomes a routine with a name and a schedule.70, 71
Pax8 (8os and 8bot)TriggersSchedules and triggers. A webhook trigger is not publishedcheckAnything you ask for regularly becomes a routine with a name and a schedule.; acts on schedules and triggers71
Pax8 (8os and 8bot)A person approves an actionEach action asks for your approvalcheckevery one of those actions still asks for your approval71
KaseyaConnects your AI toThe Kaseya platform, Claude and Microsoft Copilot Cowork, through APIsvaluean open platform built on APIs that delivers insights and automation wherever IT teams work; including the Kaseya platform, Claude and Microsoft Copilot Cowork73
KaseyaStatus on its own pagePreviewed 2026-06-17. Early access late 2026, general availability in 2027not finalEarly access to these new Kaseya Intelligence capabilities is expected in late 2026, with general availability expected in 2027.; 17 June 202673
KaseyaMSP tools on its own pagesIts own stack: Datto RMM, Autotask PSA, IT GluevalueRemote monitoring & Endpoint management Datto RMM Helpdesk & Service desk automation Autotask PSA IT documentation & knowledge management IT Glue74
KaseyaAI clients it namesClaude and Microsoft CopilotvalueAccess Kaseya Intelligence through Microsoft Copilot, Claude and other AI tools75
KaseyaPrice on its public pageNot published. Kaseya 365 offers a quotenot publishedRequest a quote76
KaseyaFree planNot publishednot publishedNo statement on the page read.76
KaseyaWhat counts against the planNot publishednot publishedNo statement on the page read.76
KaseyaSign-in and accessNot publishednot publishedNo statement on the page read.73
KaseyaWrite actionsWith technician approvalcheckwith technician approval, execute tasks, update tickets and generate reports automatically73
KaseyaAudit logNot publishednot publishedNo statement on the pages read.73, 77
KaseyaA setup for each customerNot publishednot publishedNo statement on the page read.73
KaseyaSOC 2Type II audits for its IT Complete modules. The scope for Intelligence is not statedvaluea history of exception-free SOC 2 Type II audits for a wide set of IT Complete modules78
KaseyaRuns in your own cloudNot publishednot publishedNo statement on the page read.73
KaseyaWorkflows or agentsDigital Specialists: AI specialists for a rolecheckDigital Specialists Free up time with role-level AI specialists77
KaseyaTriggersNot publishednot publishedNo statement on the page read.77
KaseyaA person approves an actionTechnician approvalcheckwith technician approval, execute tasks, update tickets and generate reports automatically73
ThreadConnects your AI toIts own service-desk tools. Its connectors bring in NinjaOne, Notion, Zapier and LinearvalueUse Super Magic connectors (Super MCP) to bring Notion, Zapier, Linear, NinjaOne, and other tools into Inbox so you can act across them from any ticket.79
ThreadStatus on its own pageIts MCP server is generally available to all partnersvalueAvailability: generally available to all partners.80
ThreadMSP tools on its own pagesBuilt on ConnectWise, Autotask and HaloPSAvalueThread is the AI service desk for MSPs on ConnectWise, Autotask, and HaloPSA81
ThreadAI clients it namesClaude Desktop, ChatGPT, Cursor, or any MCP clientvalueConnect Claude Desktop, ChatGPT, Cursor, or any MCP client to Thread's service-desk API via OAuth 2.1 to search tickets, manage contacts, and run write actions.80
ThreadPrice on its public pageAI Essentials: $19 for each managed customer a month. AI Pro: $34check$19 per managed customer/mo; $34 per managed customer/mo82
ThreadFree planA 60-day money-back guaranteevalue60-Day Money-Back Guarantee82
ThreadWhat counts against the planManaged customers, not tokensvalueYour pricing is based on the number of customers you manage; there are no token meters or usage surprises82
ThreadSign-in and accessOAuth 2.1, one member for each connection. Admins choose who may connectvalueWorkspace admins can decide who is allowed to connect at all, see every app that's connected, and cut off any app with one click.; Connect Claude Desktop, ChatGPT, Cursor, or any MCP client to Thread's service-desk API via OAuth 2.1 to search tickets, manage contacts, and run write actions.83, 84, 80
ThreadWrite actionsOn Agentic plans. Other plans see read-only toolscheckWrite and integration tools appear only on Agentic plans.; On a non-Agentic plan (no AI Pro), the connection sees only the seven read-only Super Magic tools80
ThreadAudit logEvery tool call is logged under the membercheckevery tool call is logged under the member identity behind the connection.80
ThreadA setup for each customerPriced and licensed for each managed customercheckYour pricing is based on the number of customers you manage82
ThreadSOC 2Not published in its docs. Its Trust Center has a SOC 2 section that lists an engagement letternot publishedThread's certification status, continuous control monitoring, and the security documents available for request are published on the Thread Trust Center.; Compliance; SOC 2; Resources; Engagement Letter85, 86
ThreadRuns in your own cloudNot publishednot publishedNo statement on the pages read.82, 81
ThreadWorkflows or agentsA Triage Agent and a Reminder Agent, on AI ProcheckCurrently, we offer a Triage Agent and a Reminder Agent82
ThreadTriggersA Flow trigger starts an agentcheckan agent is that same skill given a Flow trigger and a write scope so it runs unattended81
ThreadA person approves an actionIt asks for confirmation before any write. An agent in a Flow runs with no confirmation of each stepcheckIt reads freely, and before any write it shows a Confirm action card; It acts only with your confirmation.; nobody confirms each step there87, 88
Bifrost (gobifrost.com)Connects your AI toAny API, through code. It has no vendor catalogvalueReach any API directly instead of waiting for a vendor connector to exist.89
Bifrost (gobifrost.com)Status on its own pageNot stated on its sitenot publishedNo statement on the page read.90
Bifrost (gobifrost.com)MSP tools on its own pagesIts README names NinjaOne, HaloPSA, Pax8 and Microsoft CSP as example integrationsvalueCreate integration modules for common platforms (NinjaOne, HaloPSA, Pax8, Microsoft CSP)91
Bifrost (gobifrost.com)AI clients it namesClaude Code, Codex, Cursor, CopilotvalueInstall the Bifrost plugin for Claude Code or Codex, or point Cursor, Copilot, or any other agent at Bifrost.90
Bifrost (gobifrost.com)Price on its public pageFree and open source (AGPL). You host itcheckAGPL, self-hosted, no per-seat pricing, no lock-in.89
Bifrost (gobifrost.com)Free planIt is free. No hosted plan is statedcheckAGPL, self-hosted, no per-seat pricing, no lock-in.89
Bifrost (gobifrost.com)What counts against the planNo per-seat pricing. No meter is statedvalueAGPL, self-hosted, no per-seat pricing, no lock-in.89
Bifrost (gobifrost.com)Sign-in and accessGoogle, Microsoft and OIDC sign-invalueGoogle, Microsoft, and OIDC sign-in.89
Bifrost (gobifrost.com)Write actionsNot publishednot publishedNo statement on the page read.89
Bifrost (gobifrost.com)Audit logExecution history, traces and costvalueExecution history, traces, and cost across everything you run.89
Bifrost (gobifrost.com)A setup for each customerA customer signs in and sees only its own datacheckPut an agent in Global and give every customer access, or deploy an app to one organization and one role. Customers sign in and see only their own data.90
Bifrost (gobifrost.com)SOC 2Not published. Its compare page says that self-hosting is your responsibilitynot publishedself-host = your responsibility92, 93
Bifrost (gobifrost.com)Runs in your own cloudYou self-host itcheckSelf-host it, read it, fork it.90
Bifrost (gobifrost.com)Workflows or agentsWorkflows, agents and apps, built in codecheckDevelop and run workflows, agents, and apps, not only for your own team but for all of your customers.90
Bifrost (gobifrost.com)TriggersWebhooks, schedules and topic eventscheckEvent sources, subscriptions, schedules, and topics to trigger reusable logic.; an HTTP endpoint that an external system (HaloPSA, Microsoft 365, a generic provider) calls.; a cron expression that fires on a recurring timer, with a timezone and an overlap policy89, 93
Bifrost (gobifrost.com)A person approves an actionNot published for agent or workflow runsnot publishedThe one approval in its docs is an administrator who approves a permission request at install.93

Text outside the grid on this page repeats grid cells and carries the same source numbers.

[ 05 // ai governance ]
[ 05 ]

AI Governance vs MSP shadow-AI tools

Sources, each checked 2026-11-15

  1. 1ShadowLock. https://shadowlock.io/pricing
  2. 2ShadowLock. https://shadowlock.io/features/ai-governance
  3. 3Shadow Defend. https://shadowdefend.com/pricing/
  4. 4Shadow Defend. https://shadowdefend.com/solutions/msp/
  5. 5Shadow Defend. https://shadowdefend.com/security/
  6. 6DefensX. https://www.defensx.com/product/
  7. 7DefensX. https://www.defensx.com/blog/everyones-talking-about-shadow-ai/
  8. 8dope.security. https://dope.security/post/shadow-ai-tools-for-msps
  9. 9dope.security. https://www.dope.security/pricing
  10. 10N-able Shadow AI Visibility. https://www.n-able.com/blog/n-able-shadow-ai-visibility-is-now-available-to-help-govern-ai-usage-n-central-n-sight-and-adlumin

Grid cells

VendorRowThe cell saysMarkThe vendor’s wordsSource
ShadowLockHow it is pricedFor each managed Windows device. 25-device minimumvaluepriced per managed device per month, billed monthly with no annual commitment and a 25-device minimum per account; A device is any managed Windows endpoint that runs the ShadowLock agent.1
ShadowLockPrice on its public pageNot published. A rate card by emailnot publishedwe will email your rate card1
ShadowLockFree planA 14-day trialvalueFree 14-day trial.2
ShadowLockClient organizationsNo cap on organizations. No fee for each usercheckUnlimited organizations; There is no per-user fee1
ShadowLockHow it sees AI useAn endpoint agent, a browser extension and a Microsoft 365 OAuth scannervalueEvery tier includes the endpoint agent, browser extension, and Microsoft 365 OAuth scanner.1
ShadowLockEndpoint agentWindowscheckA device is any managed Windows endpoint that runs the ShadowLock agent.1
ShadowLockExposure check for a clientA Microsoft 365 OAuth scannercheckMicrosoft 365 OAuth app detection1
ShadowLockChecks or blocks AI useAn allow, warn or block policy enginecheckAllow / Warn / Block policy engine1
ShadowLockHow long it keeps events90 daysvalue90-day event retention1
ShadowLockYour own storageNot publishednot publishedNo statement on the pages read.1, 2
Shadow DefendHow it is pricedFor each devicevaluePer device. Each enrolled device is $4/month3
Shadow DefendPrice on its public pagePro is $4 for each device a monthcheck$4 per device / month3
Shadow DefendFree planStarter is free, for up to 10 devicescheckUp to 10 devices3
Shadow DefendClient organizationsA policy set for each clientcheckEvery client gets its own policy set, risk rules, and audit trail.4
Shadow DefendHow it sees AI useA browser extension, deployed by MDMvalueA lightweight browser extension deploys across a client's fleet via MDM.4
Shadow DefendEndpoint agentCovers AI use in the browservalueWe govern browser-based AI use on managed devices.4
Shadow DefendExposure check for a clientNot publishednot publishedNo statement on the pages read.3, 4, 5
Shadow DefendChecks or blocks AI usePrompt inspection, with warn and block actionscheckFull prompt inspection; Warn & block actions3
Shadow DefendHow long it keeps events7 days on Starter, 90 on Pro, 365 on EnterprisevalueData retention 7 days 90 days 365 days3
Shadow DefendYour own storageStorage location not stated. It stores prompt text itselfnot publishedNon-sensitive prompt text is stored to give you a usable audit record.5
DefensXHow it is pricedNot published. Its page says it has flexible pricing tiersnot publishedYes! We offer flexible pricing tiers6
DefensXPrice on its public pageNot publishednot publishedNo statement on the page read.6
DefensXFree planTrial subscriptions are availablevalueTrial subscriptions are also available.6
DefensXClient organizationsOne multi-tenant consolecheckfrom one multi-tenant console7
DefensXHow it sees AI useAn agent and a browser extension, on managed and unmanaged devicesvalueIt runs as a lightweight agent and a browser extension, across managed and unmanaged devices alike7
DefensXEndpoint agentA lightweight agentcheckIt runs as a lightweight agent and a browser extension, across managed and unmanaged devices alike7
DefensXExposure check for a clientA self-assessment scorecard, with no sign-upcheckSeven questions, about sixty seconds, no sign-up.7
DefensXChecks or blocks AI useKeeps a record of AI prompts. Prompt logging is in its Premium packagevaluekeep a record of AI prompts; LLM Prompt Logging7, 6
DefensXHow long it keeps events30 days on Core packages, 90 days on Premiumvalue30-day Log Retention; 90 Day Log Retention6
DefensXYour own storageNot publishednot publishedNo statement on the page read.6
dope.securityHow it is pricedNot publishednot publishedNo statement on the pages read.8, 9
dope.securityPrice on its public pageNot publishednot publishedNo statement on the pages read.8, 9
dope.securityFree planA free trial with no card. The length is not statedvaluedope.security's instant trial needs no payment method; Feel confident before you buy and try it completely free.8, 9
dope.securityClient organizationsOne MSP login switches between customer tenantscheckone MSP login switches between customer tenants8
dope.securityHow it sees AI useAn endpoint agent, with the proxy on the devicevaluedope.security puts the proxy on the device.8
dope.securityEndpoint agentMac and Windowscheckit's an endpoint agent for Mac and Windows8
dope.securityExposure check for a clientNot publishednot publishedNo statement on the page read.8
dope.securityChecks or blocks AI useBlocks personal accounts. DLP in Monitor, then BlockcheckDopamine DLP in Monitor, then Block; personal-account blocking8
dope.securityHow long it keeps eventsNot publishednot publishedIts seven-day figure is a dashboard view, not a retention period.8
dope.securityYour own storageNot published. It can stream to a SIEM or to an AWS S3 bucketnot publishedevery client tenant can stream web transactions to Splunk, QRadar, Microsoft Sentinel, CrowdStrike, Taegis, or Datadog over HTTP, or to an AWS S3 bucket for any SIEM8
N-able Shadow AI VisibilityHow it is pricedNot published. Its post says to contact N-ablenot publishedContact your N-able representative or visit n-able.com for details.10
N-able Shadow AI VisibilityPrice on its public pageNot publishednot publishedNo statement on the page read.10
N-able Shadow AI VisibilityFree planNot publishednot publishedNo statement on the page read.10
N-able Shadow AI VisibilityClient organizationsA view by tool, user, device and organizationvalueA dedicated AI Usage tab with views by tool, user, device, and organization10
N-able Shadow AI VisibilityHow it sees AI useAn endpoint scan and DNS traffic analysis, with no new agentsvalueDetection runs through existing technology, with no new agents, no new tools, and no additional infrastructure required.; Network-based detection: DNS traffic analysis10
N-able Shadow AI VisibilityEndpoint agentNo new agentsvalueDetection runs through existing technology, with no new agents, no new tools, and no additional infrastructure required.10
N-able Shadow AI VisibilityExposure check for a clientNot publishednot publishedNo statement on the page read.10
N-able Shadow AI VisibilityChecks or blocks AI useNot publishednot publishedNo statement on the page read.10
N-able Shadow AI VisibilityHow long it keeps eventsNot publishednot publishedNo statement on the page read.10
N-able Shadow AI VisibilityYour own storageNot publishednot publishedNo statement on the page read.10

Text outside the grid on this page repeats grid cells and carries the same source numbers.

[ 06 // left out ]
[ 06 ]

Left out, and why.

  • Lists of MSP tools that a search did not find in a vendor’s catalog (n8n, Pipedream, Cloudflare). A missing search result is not a fact about the vendor.
  • Whether Kaseya has an MCP server. No Kaseya page that was read uses the term, so the grid says nothing either way.
  • Bifrost by Maxim AI. It is another product with the same name. The column is Bifrost at gobifrost.com.
  • Counts that a vendor’s own pages disagree on: WYRE’s vendor count (two pages, two numbers), n8n’s integration count and Zapier’s action count. Each cell uses the figure from the page it cites.
  • Action counts for single apps in a catalog (Pipedream). A count shows coverage and is not a score.
  • Hatz AI’s cap on active tools in one chat. It comes from a document dated 2026-10-01, and a later release note does not say whether it changed.
  • Roadmap items, such as N-able’s planned client registration.
  • Add-on prices (Thread), a second plan table (Composio’s Platform tab) and plan prices above the first paid plan, except where a cell needs them.
  • MSP360’s extra controls (IP allowlist, time-limited access). There is no matching row.
  • The line in WYRE’s getting-started FAQ that says Conduit is not a workflow tool. Its workflows guide describes workflows that Conduit runs, and the cell cites the guide.
  • Halo’s warning about its “Include all system tools” option, NinjaOne’s Katana AI controls, and every tool count on the vendor-server page. These stay out.
  • DefensX’s own caveat about its scorecard, and Shadow Defend’s wording about a committed minimum (its own pages disagree).
  • A SOC 2 row on the AI Governance page, a worked price example, and the products outside each comparison (Acronis, Check Point, FireTail, Microsoft Purview, MSPlex, MCPconnect, MSPbots).