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 that the token can be stored permanently in config or used for a session, and that calling with no args yields a link. This adds behavioral context beyond the annotations (e.g., idempotentHint, readOnlyHint). It also clarifies that the token is a JWT, which is useful. No contradictions with annotations.
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 somewhat verbose, starting with 'MCP.AI for IDE agents' which is context but not essential to the tool's function. The flow is a bit rambling: 'log in in the browser, copy the access token' and then 'Or paste it here...' could be tightened. However, it's structured with examples and options, making it acceptable.
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 simple tool with one optional parameter and no output schema, the description adequately covers the two usage scenarios (permanent vs session) and the no-argument behavior. It doesn't describe success/failure responses, but given its simplicity and lack of output schema, this is sufficient.
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 only lists 'token' as a string with no description, leaving 0% coverage. The description compensates by explaining the token is a JWT and that it's optional—calling with no args returns a link, while providing a token performs session login. This adds clear semantic meaning to the parameter.
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 authentication, describing the login process and token handling. It doesn't explicitly distinguish from siblings like 'connect', but the action is specific enough. The text references logging in and accessing tokens, making the purpose unambiguous.
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 usage instructions: either add a token to the server config for permanent access or pass it as a parameter for session-only login, and explains that calling with no arguments returns a link. It gives concrete examples of when to use each approach, though it doesn't mention alternative tools.
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.
The set mixes platform-level tools (connect, toolkit_info) that both report connection status, and marketplace is an overloaded catch-all. The four transparencia_* tools are distinct, but overall there are boundary ambiguities that descriptions only partially resolve.
The data tools follow a clear transparencia_<domain>_<entity> pattern, but the platform tools are a mix of bare verbs (authenticate, connect), nouns (marketplace), and verb_noun compounds (report_bug, show_version, toolkit_info). Mixed conventions but readable.
At 10 tools, the count is within a reasonable range, but only 4 are actually transparency-related data tools; the other 6 are MCP platform utilities that feel out of place for a CGU-focused server, making the set slightly over-scoped.
The transparency data coverage is thin: it has expense documents, aggregate expenses, PEP, and sanctions, but lacks many core CGU portal queries such as government employees' salaries, travel expenses, agreements, and bidding data. This leaves significant gaps for any broader transparency use case.