read thedocs.

[ docs // guides & reference ]

Connector setup guides, tool references, auth flows, and platform concepts — everything you need to run StackJack, in one place.

Browse the Docs All Connectors

34 connectors documented // 6,712 tools referenced // setup, auth & platform guides

↓

No pages match that search. Clear it

← All documentation

StackJack Platform Tools (`stackjack_*`)

Alongside connector tools, StackJack serves roughly two dozen platform tools under the stackjack_ prefix (23 today). They need no connector at all — a freshly created tenant with zero connectors configured can call them. They are the "getting started" and self-service surface for any connected harness: session diagnostics, platform status, live documentation, support tickets, automation control, and — when catalog mode is enabled — on-demand tool discovery.

Most of them are on by default. The diagnostic, live-documentation, and support-ticket tools are served to every connected harness automatically — a restricted tool selection on an MCP client does not hide them. There are two exceptions to "always on":

stackjack_run_agent triggers billed automation runs, so it still requires an explicit per-client grant (plus the Agentic Orchestration feature).
The five catalog-mode tools appear only when your organization has catalog mode enabled — they exist to power that feature's on-demand discovery, and a connection using the full tool list never sees them.

Everything else on this page is available to any connection without being selected.

The always-available diagnostic set

These eight diagnostic tools are visible to every connected client — they can't be deselected, because they change nothing in StackJack or your connected products and exist so any harness can diagnose itself. (Seven are flagged read-only in their MCP metadata; stackjack_refresh_tool_list is technically an action — it asks your harness session to refresh — but it still mutates no data.)

Tool	What it does
`stackjack_session_info`	Shows your session context: tenant, MCP client, each active connector with its plan, monthly call limit, and whether credentials are configured, plus how many tools are accessible versus the total.
`stackjack_list_tools`	Lists the tools available to your tenant with each tool's required plan and an `accessible` flag. Supports optional filters by category (standard/advanced/premium) and by connector (the filter accepts any connector name or common alias across all connectors — for example halo, connectwise, meraki, ncentral, or eset).
`stackjack_health_check`	Live-validates the stored credentials of every configured connector against its vendor API and reports status, latency, and error detail per connector (a connector whose stored credentials can't be loaded is reported as `unavailable` and retryable rather than being probed). Pass an optional `connector` filter to probe just one. If your workspace has no connectors configured, it returns a `no_connectors` status pointing you to the portal; you can also validate any connector on the portal's Connectors page.
`stackjack_get_service_status`	Overall StackJack service status, component statuses, maintenance notices, advisories relevant to your connectors, and the current tool-catalog version.
`stackjack_list_advisories`	Lists published advisories, filterable by kind (incident, maintenance, advisory, release, tool recommendation), severity, connector, or tool name.
`stackjack_get_release_notes`	Tool-catalog release and patch notes; ask "what changed since version X" with the `sinceVersion` parameter.
`stackjack_get_tool_guidance`	Operator-published guidance for a specific tool — for example a deprecation notice with the recommended replacement.
`stackjack_refresh_tool_list`	Asks your harness session to refresh its StackJack tool list. Best effort — some harnesses ignore the refresh notification, in which case disconnect and reconnect.

The "pending approval" signal

If a team member connects before an admin has assigned them any tools, stackjack_session_info returns a special pending_approval response telling the AI (and the user) that the connection works but an admin needs to approve them on the Team page and assign tool permissions. If a teammate reports "it connects but nothing works," ask them to run this tool first.

Live documentation tools (always available)

Three tools let a harness read StackJack's own product documentation and browse the tool catalog on demand — so the AI can answer "how do I connect Halo?" or look up a tool's schema without leaving the conversation. Like the diagnostic set, they are served to every connected client automatically and are never plan-gated.

Tool	What it does
`stackjack_search_docs`	Searches StackJack's product documentation (how-to guides, connector setup, concepts) and returns ranked page matches — slug, title, section, and a snippet — without full page bodies.
`stackjack_get_doc_page`	Fetches one documentation page by slug (from a `stackjack_search_docs` hit) as cleaned markdown, with its title, section, and headings.
`stackjack_get_tool_catalog`	Discovers the full StackJack tool catalog grouped by connector — an overview of per-connector counts and tiers, or a single connector's tools (optionally with full input schemas).

Support ticket tools (always available)

Four tools let a harness open and follow up on StackJack support tickets. They are served to every connected client automatically — they don't need to be selected, and a restricted tool selection never hides them.

Tool	What it does
`stackjack_create_support_ticket`	Files a new support ticket for your organization.
`stackjack_list_support_tickets`	Lists your organization's tickets with status and priority.
`stackjack_get_support_ticket`	Fetches one ticket with its full message thread.
`stackjack_add_support_ticket_message`	Adds a reply to a ticket (replying to a closed ticket reopens it).

When a connector tool fails, its error response includes a ready-made support ticket draft and a suggested next action pointing at stackjack_create_support_ticket — the AI is instructed to ask for your authorization before opening a ticket (details). Ticket creation also automatically attaches diagnostic context so StackJack support can investigate without a back-and-forth. Abuse guards (an hourly per-tenant ticket cap and short-window duplicate suppression) prevent a misbehaving agent from flooding support.

Automation tools (feature-gated)

Three tools let a harness discover and run your StackJack Automations. All three require the Agentic Orchestration feature (enabled for your tenant by StackJack on request — contact support); when the feature is off they are hidden from discovery and any direct call returns a feature_disabled error. Once the feature is on, they split by risk:

stackjack_list_agents and stackjack_get_run_transcript are served to every connected client automatically — like the other platform tools, a restricted tool selection doesn't hide them.
stackjack_run_agent is the only platform tool that still needs an explicit per-client grant, because it triggers billed agent runs. A client with no tool restriction gets it automatically once the feature is on; a client with a restricted selection must include it in that selection.

Tool	What it does
`stackjack_list_agents`	Lists the automations that are exposed to harnesses — only those that are active, consent-accepted, on-demand, and ready to run. Discovery deliberately matches what `stackjack_run_agent` would accept.
`stackjack_run_agent`	Runs an automation by id or name and returns a summary. Only works for automations marked "Expose as MCP tool" with the on-demand trigger type; scheduled and webhook automations can't be manually invoked from a harness.
`stackjack_get_run_transcript`	Fetches the full turn-by-turn transcript of a finished run (tool calls, results, and the final message) — more detail than the run summary. Long transcripts paginate via a `page` parameter and a `has_more` flag.

If all execution slots are busy, stackjack_run_agent returns a retryable capacity_exceeded error — try again shortly.

Catalog-mode tools (only in catalog mode)

When your organization enables catalog mode — the feature that serves a harness a small, searchable tool surface instead of the full multi-thousand-tool list — five more platform tools appear to power on-demand discovery and dispatch. They are not shown otherwise: a connection using the full tool list never sees them. All five are Free (never plan-gated).

Tool	What it does
`stackjack_search_tools`	Searches every tool your tenant can access by a natural-language query and returns ranked matches with each tool's plan, safety flags, and how to run it in the current mode.
`stackjack_describe_tools`	Returns the full description, required plan, safety flags, and JSON input schema for up to 10 named tools — inspect a tool before running it.
`stackjack_run_readonly_tool`	Runs a read-only connector tool by name and returns its raw JSON. Refuses non-read-only tools (use `stackjack_run_tool`). Because it's read-only, a well-behaved harness can auto-approve it.
`stackjack_run_tool`	Runs any connector tool your tenant can access by name — including writes and destructive actions. Your harness prompts for approval on every call, since it can't see the underlying tool.
`stackjack_platform`	Minimal-mode router: runs a StackJack platform tool by name, folding the platform tools into one entry for the tightest tool budgets.

Dispatching a tool through stackjack_run_readonly_tool, stackjack_run_tool, or stackjack_platform runs the real tool with every permission, subscription, and safety check applied exactly as a direct call — and usage is attributed to the tool you actually ran, not the dispatcher. For how modes, pins, and opt-in work, see Choosing tools for each client.

Do platform tools count against my quota?

Platform tools are not connector calls, and monthly allowances are per connector — using the diagnostic tools freely will not consume any connector's allowance.