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 declare idempotentHint=true, destructiveHint=false, readOnlyHint=false, and the description does not contradict these. The description adds valuable context about persistence (permanent vs session-only) and the no-args behavior to get a link, beyond what annotations state. It stops short of explaining edge cases like invalid tokens or clearing existing sessions, but overall it discloses key behaviors.
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 front-loaded with the primary purpose and then details two usage modes and the no-args behavior. It is somewhat dense and long, but every sentence adds necessary information. No filler words or repetition.
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?
Given the tool's moderate complexity (two flows, optional token), the description covers the workflow thoroughly: browser login, token copy, config vs. session, and no-args call. It does not describe the return value or success/error behavior, but in the absence of an output schema this is a minor gap. Overall it provides enough context for an agent to select and invoke the tool 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 schema provides only the token property name with no description and 0% coverage. The description compensates fully by explaining that the token is a JWT to be pasted for session-only login, that it can be omitted to get the link, and that a permanent connection can be set via config. This gives the agent complete understanding of the parameter's purpose and optionality.
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 is for authenticating to MCP.AI for IDE agents, using a browser login and access token. It distinguishes itself from siblings by focusing solely on authentication and explaining the two login modes (permanent via config vs session-only via token). It is not a tautology and gives specific actionable steps.
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 provides clear context for when to use this tool: when setting up authentication for MCP.AI. It explains the two distinct flows (permanent config and session-only token) and how to call with or without the token parameter. However, it does not explicitly mention when not to use this tool or list alternatives, though none are apparent among siblings.
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.
Some tools overlap in purpose, particularly connect and toolkit_info both report connection status, while authenticate handles login. The marketplace tool is a large catch-all that could be confused with platform management, but its detailed description helps distinguish it.
Tool names are inconsistent: some use verb-only (authenticate, connect), some use verb_noun with underscores (report_bug, show_version), some are nouns (marketplace, toolkit_info), and one is a Portuguese descriptive phrase (cpf_cadastral_plus_consultar). The mix of languages and conventions makes the set feel chaotic.
With 7 tools, the count is within the typical well-scoped range. However, only one tool actually relates to the server's stated CPF consultation purpose, while the rest are generic platform utilities, making the set feel slightly over-inclusive.
The core CPF consultation workflow is covered (authenticate, connect, consult), but there are no other CPF-specific operations such as batch consultation, validation, or historical queries. The inclusion of many platform-management tools doesn't fill these domain gaps.