Skip to main content
Glama

Get Integration Status

get_integration_status
Read-onlyIdempotent

See every integration for this company and user in one call: what's connected (banks, HMRC MTD, Stripe, Deel, Gmail, WhatsApp, Telegram, Slack, Xero and the rest), what's available but not connected, what is coming soon and cannot be connected yet (coming_soon), and whether data is actually FLOWING through each connected feed (flowing / quiet / error, last event, 7-day event count, error message). Use when the user asks about connections or channels, asks whether or when AccountsOS connects to a named app or service, when something they need for the task at hand is not connected, or when their data looks stale or missing — a dead feed is often the real cause. To OFFER to set one up, end your message with [[connect: provider_id]] on its own line (use the provider id from this tool's result, e.g. [[connect: slack]] or [[connect: mercury]]): it renders a card. OAuth providers start sign-in; API-key providers (Mercury, Stripe, Wise, Qonto, Airwallex, Starling) collect the key on a masked in-thread field. Offer at most one connection per message. Only a provider in not_connected can be offered. One in coming_soon is planned and not live: say it is coming soon, with no date, never offer to connect it, never call it available and never say it is not planned (follow coming_soon_note). When the result carries supplier_bills_address, that is the address the company can give its suppliers so bills arrive straight in its incoming documents (it is made from the company's VAT or tax number); say it when the user asks where suppliers should send invoices. Never ask the user to paste an API key into the chat box — the card collects it, and the key is never returned to you (you only see connected true/false).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_integration_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
companyNoWhich company to read, by name or id, when the account has more than one (see list_companies). Leave it out to use the only company, or the default.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnly/idempotent/non-destructive, but the description adds real behavioral context: the result reports flowing/quiet/error, last event, 7-day event count and error message; OAuth providers start sign-in while API-key providers collect the key in a masked field; the key is never returned and only connected true/false is visible. It even discloses that ending a message with [[connect: provider_id]] renders a card, a side effect not visible in any structured field.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose and the return-shape enumeration are correctly front-loaded, and every block of guidance maps to a real decision the agent must make. It is dense and slightly over-long, with redundant emphasis around coming_soon ('never offer to connect it, never call it available and never say it is not planned') and a long inline provider list that could be trimmed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the full burden of describing return values and does so thoroughly: status categories, per-feed flow state with timestamps and counts, provider_id for the connect card, and the conditional supplier_bills_address field. Nothing an agent needs to interpret or act on the result is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is a single optional `company` parameter and the schema documents it at 100% coverage, including the list_companies pointer and the default behaviour. The description adds nothing about this parameter, so the baseline 3 applies — the schema does all the work here.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('See every integration for this company and user in one call') and then enumerates the exact facets returned: connected vs available vs coming_soon, plus live flow state. It is instantly distinguishable from siblings like get_accounts_status or get_reconciliation_status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It names four concrete trigger situations (user asks about connections/channels, asks whether AccountsOS connects to a named app, needs something not connected, or data looks stale/missing) and explicitly says a dead feed is often the cause of stale data. It also gives hard rules on alternatives and edge cases: only offer providers in `not_connected`, never offer `coming_soon`, at most one offer per message.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.