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. The description adds valuable behavioral context about the two modes (permanent vs session-only), explains token handling, and notes that calling with no args returns a link. This goes beyond the annotations without contradicting them.
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?
Three sentences convey all necessary information without fluff. The opening phrase 'MCP.AI for IDE agents (Cursor, etc.)' adds minor context but is slightly extraneous. Overall, it is well-structured and front-loaded with the core action.
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 a tool with no output schema, the description tells users to expect a link when called with no args and explains the token submission flow. It could mention the response format for token acceptance or error cases, but it is sufficiently complete for a straightforward auth tool.
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 has a single optional token string with no description. The description explains that the token is a JWT pasted by the user, and that omitting it triggers the login link workflow. This provides essential semantic meaning that the schema lacks.
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?
Description clearly states the tool's function: authenticating MCP.AI for IDE agents by logging in via browser, obtaining an access token, and establishing either a permanent or session-only connection. Uses specific verbs like 'log in', 'copy', 'add', and 'paste', and distinguishes from siblings by focusing on the authentication flow.
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?
Provides explicit usage instructions: recommends adding the token to server config for permanent connection, or pasting it for session-only login, and explains how to call without args to get the login link. This gives clear when-to-use and how-to-use 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.
Several tools overlap in reporting connection and toolkit status (connect, toolkit_info, and portions of marketplace), making it ambiguous which to call. The domain-specific tool is distinct, but the platform tools blur together.
Tool names are inconsistent: some are single verbs (authenticate, connect), some are noun phrases (toolkit_info, marketplace), and one is a long Portuguese phrase (transparencia_servidores_viagens_consultar). No consistent verb_noun pattern is present.
Seven tools is an acceptable count, but the server's stated purpose about transparency is served by only one tool, with six generic platform tools that dilute the focus. The count feels high for the domain and unfocused.
The domain tool only queries travel expenses by CPF, covering a narrow slice of what the server name implies. There are no other domain operations, such as listing available datasets or querying by other criteria, so the surface is significantly incomplete.