MCP for Claude & ChatGPT

Manage connectors

tuqui_connector

Destructive

Read and administer the workspace's connected apps. action='list' returns them with whether each is on for you; 'get' one; 'save' changes it; 'delete' removes it from the workspace (admin). scope='mine' (default on save) turns an app on or off FOR YOU ONLY; scope='workspace' edits the app itself and requires admin. 'connect' shows the person a card with the apps they still have to authorize with their own account (Gmail, Drive, Microsoft 365…), each with a button to the app's consent screen; it connects nothing by itself. Use it when someone asks to connect, link or authorize an app, or when you need an app they have not connected, without listing first. Pass 'apps' with the ones they named. Registering a new connector is NOT here — it needs a URL, a transport and a consent screen, and lives on the Connectors page.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "tuqui_connector"
  }
}

Input Schema

Name	Required	Description
`apps`	No	'connect': the apps the person named, as they said them ('Gmail', 'Google'). Without it, the card shows every app they can still connect.
`name`	No	scope='workspace'. Refused on platform apps.
`scope`	No	'mine' (default): turn the app on or off for yourself. 'workspace': edit the app for everyone — requires admin.
`action`	Yes	REQUIRED. What to do with the connectors.
`active`	No	scope='mine': whether this app is available in YOUR chats.
`enabled`	No	scope='workspace': whether the app is on for the whole workspace.
`description`	No	scope='workspace'. Refused on platform apps.
`connector_id`	No	UUID. Required for 'get', 'save' and 'delete'.
`consent_token`	No	The approval a person gave for THIS call in Tuqui. Bound to these arguments and valid once.
`expose_over_mcp`	No	scope='workspace': whether this app's tools are re-published on Tuqui's own MCP server, for clients connecting from outside.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 6, 2026

addedInput schema / properties / apps

Added value: +{
+  "description": "'connect': the apps the person named, as they said them ('Gmail', 'Google'). Without it, the card shows every app they can still connect.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

First observedNov 2, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description substantiates that with concrete consequences: 'delete' removes the app from the workspace and requires admin, 'save' mutates the app, workspace edits affect everyone. It adds genuinely non-obvious behavior the annotations cannot convey — that 'connect' only shows a consent card and 'connects nothing by itself', and that consent_token is single-use and bound to the exact arguments. It does not cover rate limits or confirmation requirements for the destructive action, keeping it short of a 5.

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?

Front-loaded with the action list, then scope rules, then the 'connect' workflow and the explicit exclusion — a sensible ordering with no filler sentences. It is dense and parenthetical-heavy ('(admin)', '(Gmail, Drive, Microsoft 365…)'), which slows parsing slightly, but each clause carries distinct operational information.

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

Completeness4/5

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

For a 10-parameter, no-output-schema tool with destructive and admin-gated paths, the description covers action semantics, scope semantics, the consent-card workflow, and the out-of-scope registration case. The notable gap is internal consistency: the prose describes an action='connect' mode that does not appear in the schema's action enum, which could lead an agent to issue an invalid call; the destructive-delete confirmation expectation is also left implicit.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline would be 3, but the description adds cross-parameter meaning the schema does not: which parameters pair with which action/scope ('active' only for scope='mine', 'name'/'description' only for scope='workspace' and refused on platform apps), that 'mine' is the default on save, and how the 'apps' argument should be phrased from the user's own words. This materially reduces misuse of the 10-parameter surface.

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 names the resource ('the workspace's connected apps') and enumerates what each action does: 'list' returns them with per-user on/off state, 'get' one, 'save' changes it, 'delete' removes it. It also explicitly excludes the adjacent-but-different operation ('Registering a new connector is NOT here'), so an agent can separate it from connector-registration tooling without reading the schema.

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 states precisely when to reach for the 'connect' path ('when someone asks to connect, link or authorize an app, or when you need an app they have not connected, without listing first') and names the alternative behavior (don't list first). It also gives the selection rule between scopes and the admin gate on scope='workspace', plus where the out-of-scope registration task lives.

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

All MCP for Claude & ChatGPT tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.