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 indicate idempotent and non-destructive behavior. The description adds transparency by explaining that passing a token authenticates, while omitting it returns a login link. It also distinguishes between permanent and session-only connections. However, it doesn't detail any potential side effects (e.g., whether the token is stored server-side), which would be a minor gap, but the annotations already provide safety context.
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 clear and logically structured, but it contains some redundancy (e.g., 'log in in the browser, copy the access token' and later 'paste it here'). It could be condensed slightly, but the information is well-organized and not overly verbose, earning a score above mid-range.
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 absence of an output schema, the description covers the main functional outcomes: authenticating with a token and obtaining a login link. It does not specify the exact return format, but that is not strictly required. The context is sufficient for most use cases, making it complete enough for a tool with this simplicity.
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 defines 'token' as an optional string. The description significantly enriches this by explaining that providing a token authenticates directly, while omitting it triggers the retrieval of a login link. This clarifies the parameter's purpose and the behavior in both cases, fully covering the semantic gap.
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's purpose: authentication for MCP.AI IDE agents. It explicitly mentions logging in, obtaining an access token, and using it either as a permanent header or session-only login. This is specific and distinct from the sibling tools (connect, detran_pi_multas_consultar, etc.).
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 concrete usage instructions: how to obtain a token (via browser), and two ways to authenticate (permanent config header or session-only token parameter). It also explains the behavior when no arguments are provided (getting a login link). While it doesn't explicitly compare to alternatives, it gives clear 'when and how' guidance, justifying a score above average.
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.
Each tool has a clearly distinct purpose: authentication, connection, marketplace operations, bug reporting, version display, toolkit state, and the single DETRAN query. No two tools overlap in function, so an agent can easily tell them apart.
All names use snake_case and are lowercase, but the pattern is inconsistent: sometimes verb-only (authenticate, connect), sometimes verb+noun (show_version, report_bug), sometimes noun+verb (detran_pi_multas_consultar), and sometimes noun-only (marketplace, toolkit_info). There's no consistent verb_noun pattern across the set.
7 tools is within the typical range, but the majority are generic platform utilities (authenticate, marketplace, etc.) unrelated to the server's stated purpose (DETRAN PI fines). Only one domain-specific tool exists, so the count is not well-aligned with the apparent scope.
The only domain tool is detran_pi_multas_consultar, which handles a single query operation. There are no other fine-related operations (e.g., list, payment, history), so for the declared purpose the coverage is minimal. The additional platform tools don't address the domain.