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 behavioral traits beyond annotations: the permanent vs. session-only distinction, the requirement to login in the browser, and that no args returns a link. Annotations already indicate idempotency and non-destructiveness, and the description adds useful context without contradiction.
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 concise and tightly structured, using a colon and alternatives to front-load the tool's purpose. Every sentence conveys necessary information about configuration, session login, and the no-arg behavior.
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 key use cases and the return behavior (link vs. session). Lacking an output schema, it adequately describes what the tool does, though it doesn't explicitly state error handling or the exact response after successful token submission.
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 has one optional string parameter with no description (0% coverage). The description fully compensates by explaining the token parameter: 'call with { token: "<jwt>" } after the user pastes' and 'with no args to get the link'.
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 indicates this tool enables authentication to MCP.AI for IDE agents, including the browser login flow and token handling. However, it does not explicitly distinguish it from sibling tools like 'connect' or specify when not to use it.
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: the recommended permanent approach via config header, a session-only login by passing a token, and getting the login link with no arguments. It also states the trigger ('after the user pastes') for using the token parameter.
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 clearly distinct purposes (auth, query, status, feedback, version, toolkit state). However, marketplace is a mega-tool that includes report_bug functionality, creating some overlap with the dedicated report_bug tool, and connect/toolkit_info both relate to connection status.
Naming is inconsistent: camelCase (connect, report_bug), snake_case (cgu_consultar), and mixed patterns overall. Also, cgu_consultar is Portuguese while other tool names are English, breaking a predictable convention.
Seven tools is a reasonable count, but the marketplace tool is overloaded with many sub-actions (search, describe, invoke, install, subscribe, etc.), making it feel like a large number of hidden tools bundled into one.
The server's primary domain is CGU data consultation, but only one tool (cgu_consultar) addresses that domain. The rest are platform utilities (auth, marketplace, version, etc.), leaving obvious gaps such as different consultation types, data explanations, or batch operations.