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?
Annotations already declare idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful context about non-expiring vs session-only login and the browser link flow, but does not disclose behaviors like whether calling with no args invalidates existing sessions or how the token is validated/stored beyond the config header recommendation. Given annotation coverage, a 3 is fair, but more detail about the exact side effects (e.g., does session token overwrite config?) would improve it.
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 three sentences, front-loaded with the audience and purpose, and covers all critical usage paths. It is slightly dense and could be broken into clearer steps, but every sentence adds necessary information about login modes and the recommended config approach. No wasted words.
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?
For an auth tool with minimal schema (one optional string) and no output schema, the description covers the workflow well: browser login link, token paste, session vs permanent. It lacks explicit mention of what the tool returns (e.g., success message) or error handling, but given the simplicity of the inputs and adequate annotations, the description is largely complete. Minor gap around post-login state verification.
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?
Schema coverage is 0% and the only parameter 'token' has no description, so the description carries the full burden. The description clarifies that 'token' is an optional JWT for session-only login, and that omitting it yields the link. This compensates well for the schema's lack of detail, but does not explain token format/expiry beyond calling it a JWT.
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 this tool handles authentication for MCP.AI IDE agents: it provides a browser login flow, accepts a pasted JWT token for session login, and explains the permanent config-based alternative. The verb 'log in' plus the resource (MCP.AI server access) and the distinct paths make the purpose unambiguous, even though there are no direct sibling login tools.
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 explicitly explains when to use each mode: 'call with { token: "<jwt>" } after the user pastes' for session-only login, or 'no args to get the link' for browser login. It also recommends the config-header approach as the best permanent alternative, giving clear decision guidance.
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.
Most tools have clear distinct purposes: cnd_federal_consultar is the only domain-specific tool, while others handle authentication, connection status, marketplace, feedback, version, and toolkit overview. The main overlap is between 'connect' and 'toolkit_info', which both report connection status, but they serve slightly different scopes (provider connections vs. overall toolkit state).
Naming is inconsistent: most tools are lowercase snake_case (e.g., report_bug, show_version), but some are single words (authenticate, connect, marketplace). The domain tool 'cnd_federal_consultar' is in Portuguese while everything else is English, breaking consistency. The mix of verbs and nouns further weakens any predictable pattern.
Seven tools is within the ideal range, but the server is named 'CND Federal' yet contains only one tool related to that domain; the other six are general platform management tools (marketplace, toolkit_info, etc.). This makes the set feel over-scoped for the apparent purpose, though the total count is acceptable.
For the CND lookup function, the single tool covers the core need (query by CPF/CNPJ), but there are no additional operations like validation, history, or credit checks. The broader platform tools provide substantial coverage for the marketplace, but they are unrelated to the CND domain, leaving the CND surface minimal and potentially incomplete for a dedicated CND service.