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 idempotent, non-read-only, non-destructive. The description adds context about permanent vs session-only behavior and link retrieval, which goes beyond annotations. No contradictions.
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 approximately three sentences but contains a long, run-on middle sentence. Information is useful but could be more tightly structured; some redundancy exists (e.g., 'paste it here').
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 simple single-parameter tool, the description covers the main behavior, modes, and parameter usage. It lacks explicit return value details, but no output schema exists and the behavior is sufficiently implied.
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 token parameter with no description (0% coverage). The description explains the token parameter semantics: call with {token} for session login, or no args to get the link, effectively documenting both states. It doesn't detail token format but compensates adequately.
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 authenticates to MCP.AI for IDE agents, describing the login flow (browser, token copy) and two usage modes. However, it does not explicitly differentiate from the 'connect' sibling, so it stops short of full distinction.
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 gives explicit guidance for two scenarios: using a config header for permanent connection versus pasting a token for session-only login, and no-args to get a link. It lacks explicit when-not-to-use alternatives to siblings, but provides clear context.
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 platform-management tools overlap in purpose: authenticate and connect both deal with connection state, while show_version and toolkit_info both return platform status. The marketplace tool is an overloaded catch-all that handles searching, invoking, installing, and billing, making it unclear when to use it versus the other tools.
Naming conventions are mixed: some tools follow verb_noun patterns (authenticate, connect, report_bug, show_version), while others are bare nouns (marketplace, toolkit_info). Additionally, the only domain-specific tool uses Portuguese (veiculo_nacional_consultar) while the rest use English, creating a language inconsistency.
The server is named 'Consulta Veicular Nacional' and appears focused on vehicle lookup, yet only 1 of 7 tools actually performs that function. The other 6 are generic platform utilities unrelated to the stated purpose, making the tool count feel bloated and off-target for the server's apparent scope.
For the core domain of vehicle consultation, the single tool veiculo_nacional_consultar provides the essential lookup-by-plate capability with no obvious missing operations. Since it is a read-only public data consultation, CRUD coverage is unnecessary, and the vehicle-related surface appears complete. The extra platform tools do not fill any domain-specific gap.