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 explains behavioral nuances such as permanent vs session-only connections and the need to copy the token from the browser. It doesn't contradict annotations (idempotentHint=true, destructiveHint=false) and provides sufficient context for a read-like, non-destructive action.
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 slightly long but well-structured: it starts with purpose, then gives the best practice, then the alternative session login. Every sentence adds value, though some trimming could make it more concise.
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 one optional parameter and no output schema, the description is complete. It covers both usage modes, the user action required, and the permanent/session distinction, leaving no critical gaps.
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?
Even though schema coverage is 0%, the description thoroughly explains the single token parameter, specifying it as a JWT to be passed after the user pastes it. It also clarifies the behavior when no arguments are provided, fully compensating for the lack of schema documentation.
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: to authenticate the user with MCP.AI by obtaining a link for browser login or accepting a token. It distinguishes from siblings like connect and marketplace by focusing solely on authentication.
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?
Explicitly explains when to use each mode: no args to get a link, or with token for session login. Also presents the preferred alternative of adding the token to config for permanent access, making the decision clear.
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 utilities (authenticate, connect, show_version), a bug reporter, and one domain-specific Brazilian vehicle-docs query tool (ecrvsp_docs_escolher_placa_consultar). The `marketplace` tool is the worst offender: its description claims it can search, describe, invoke, install, subscribe, and handle prompts—an entire parallel application that an agent would have no reason to distinguish from the main server. authenticate/connect also blur around connection state vs. action.
Conventions are mixed: single-word bare verbs (`connect`, `authenticate`), snake_case `verb_noun` (`report_bug`, `show_version`), a noun phrase (`toolkit_info`), and a long Portuguese snake_case string (`ecrvsp_docs_escolher_placa_consultar`). The inconsistent Portuguese/English mix and inconsistent verb-first vs. noun-first patterns make the surface unpredictable.
At 7 tools, the count is right in the sweet spot, and most are generic platform utilities that plausibly need to exist. However, six of the seven are generic infrastructure, leaving only one tool to represent the actual product domain, while `marketplace` crams dozens of capabilities into a single mis-sized tool. The count looks fine numerically but is lopsided in practice.
The domain (ECRVSP plate selection/consultation) has exactly one operation: `consultar` (query). There is no way to save a plate, view historical lookups, retrieve a document/receipt, handle multiple document types, or resolve a failed lookup—so any multi-step workflow hits a dead end immediately. The `marketplace`'s wrapper capabilities don't fill these gaps, and the actual product surface feels like just one CRUD read among many missing operations.