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?
It goes beyond annotations by explaining that token can be stored permanently via config header or used session-only, and that calling with no args returns a login link. This enriches the idempotent/read-only hints with practical behavior. No contradiction 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 a single long, run-on sentence that packs many details together. While it is not excessively long, restructuring could improve readability. It earns a neutral score for being informative but not perfectly 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?
Given the tool's simplicity (one optional param, no output schema), the description covers the essential information: how to authenticate permanently or per-session, and what to expect when called without arguments. It is sufficiently complete for an agent to use correctly.
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?
With 0% schema coverage, the description compensates well by explaining the 'token' parameter as a JWT and showing how to use it, including the no-argument case. It clarifies optionality and context beyond the bare schema.
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 is for authenticating with the MCP.AI service from IDE agents, explaining the login flow with a browser and access token. It distinguishes the authentication purpose from sibling tools like 'connect', though the opening phrase 'MCP.AI for IDE agents' is slightly awkward but does not obscure meaning.
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 direct instructions on how to authenticate (configure header, pass token, or call with no args) but does not explicitly contrast when to use this vs. sibling tools like 'connect'. The usage context is implied rather than stated as a choice among alternatives.
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 tools have unclear boundaries: authenticate, connect, and toolkit_info all deal with authentication/connection state, while marketplace is a catch-all that includes searching, invoking, installing, and managing MCPs. Only tribunal_trt7_processo_consultar is clearly distinct, but the generic platform tools overlap enough to create selection risk.
Naming is inconsistent: one-word verbs (authenticate, connect), nouns (marketplace, toolkit_info), snake_case verb_noun pairs (report_bug, show_version), and a Portuguese noun-infinitive combo (tribunal_trt7_processo_consultar) are mixed together. There is no clear, predictable naming convention across the set.
Seven tools is a reasonable number overall, but the set is lopsided: six tools are generic platform-management utilities and only one tool actually serves the named Tribunal TRT7 domain. The count feels acceptable for the platform shell but thin and somewhat off-purpose for a consultation server.
The single domain-specific tool likely covers the core 'consulta processual' lookup, but there are no other tribunal-specific tools for searching by different criteria, retrieving extended case details, or handling related follow-up actions. The rest of the tools are generic infrastructure, so the domain surface is minimal and leaves notable gaps for broader process-consultation workflows.