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 goes beyond the annotations by explaining session-only vs. permanent connection behavior, the no-args link flow, and what happens if a token is pasted. It is consistent with the idempotentHint annotation since logging in repeatedly is the intended, repeatable operation.
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 informative but somewhat cluttered with phrases like 'MCP.AI for IDE agents (Cursor, etc.)' and the parenthetical that is not strictly necessary. Still, every behavioral instruction has a purpose, so it is near-optimal despite its density.
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, no output schema, and annotations already in place, the description is complete enough: it explains all invocation paths and the auth/token context. No important behavior is omitted.
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 input schema only identifies 'token' as an optional string with 0% description coverage. The description compensates fully by explaining '<jwt>' and that the token results from pasting a user-provided access token, as well as clarifying the no-argument variant.
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 that this tool is for authenticating an IDE agent by either returning a login link or accepting a pasted JWT access token. It distinguishes the authentication flow from general connection/marketplace tools, though it doesn't explicitly contrast alternatives like 'connect'.
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 on when to use each mode: permanent config via Authorization header is the best option, session-only login is done by passing the token, and calling with no args returns the login link. It also states how to invoke each choice clearly.
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: auth, connection status, marketplace, bug reporting, version, toolkit info, and the domain-specific process query. No two tools overlap in functionality, and descriptions clearly differentiate them.
All names use snake_case, but the pattern is inconsistent: some are verbs (authenticate, connect, report_bug, show_version) while others are nouns (marketplace, toolkit_info, tribunal_trt10_processo_consultar). The domain tool's name is unusually long and specific, further breaking uniformity.
The server is intended for TRT10 process consultation, yet 6 of 7 tools are generic platform utilities unrelated to the domain. Only one tool actually performs the stated purpose, making the set poorly scoped for the server's user-facing role.
The domain surface consists of a single query tool (tribunal_trt10_processo_consultar) with no supporting operations like search variants, history, or bulk actions. While it may cover a simple 'consult by process number' workflow, any additional need within the domain would fail, and the platform tools do not address domain-specific gaps.