MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header Authorization: Bearer <token> for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "" } after the user pastes, or with no args to get the link.
| Name | Required | Description | Default |
|---|---|---|---|
| token | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses the behavioral implications beyond annotations: it explains the difference between permanent (non-expiring) and session-only connections, mentions the side effect of modifying server config, and indicates that no-args returns a link. This adds meaningful context that annotations (idempotentHint, destructiveHint) do not fully cover.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is structured with clear alternatives and is front-loaded with the target audience. It is slightly verbose but every sentence serves a purpose, covering the why, how, and when. A more compact version could exist, but this is still efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the full authentication flow, including token acquisition and both usage modes. It doesn't detail return values or error handling, but given the simple tool signature (1 optional parameter, no output schema) and existing annotations, it is sufficiently complete for an agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The sole parameter 'token' is fully explained as a JWT to paste after the user pastes it, and its optionality is made clear: calling with no args returns a link. This completely compensates for the 0% schema description coverage, giving the agent all needed semantic information.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: authenticating to MCP.AI for IDE agents. It explains the login flow ('log in in the browser, copy the access token') and provides two distinct usage modes, distinguishing it from sibling tools like 'connect' and 'marketplace' by focusing specifically on auth.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit guidance on when to use each approach: adding the token to the server config for a permanent connection, or pasting it for a session-only login. It also explains the no-args flow to get the link, covering all usage scenarios clearly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools have overlapping responsibilities: 'connect' and 'toolkit_info' both return connection/status info, 'authenticate' handles session/auth concerns, and 'marketplace' bundles numerous actions (including install, subscribe, cancel, report_bug) that duplicate capabilities of 'report_bug' and other tools. Agents would struggle to choose the right tool without examining internal action parameters.
Tool names follow no consistent pattern: some are bare verbs ('authenticate', 'connect'), some are verb_noun ('report_bug', 'show_version'), one is a noun ('marketplace'), and the domain-specific tool uses a long Portuguese composite ('transparencia_servidores_completa_consultar'). The mix of English platform verbs and a Portuguese domain name adds inconsistency.
Seven tools is within an acceptable range, but the 'marketplace' tool is a monolithic catch-all containing search, describe, invoke, install, list, subscribe, cancel, report_bug, request_mcp, and prompt management, effectively representing 12+ operations under one tool. This makes the actual surface area much larger than the count suggests, though the number itself is reasonable.
The server's stated purpose is federal employee transparency, but only a single CPF query tool is provided, with no listing, filtering, or batch operations. The platform admin tools (authenticate, connect, marketplace, etc.) are comprehensive, but they don't cover the transparency domain, which appears to be the server's primary focus. Many common transparency needs remain unsupported.