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 adds behavioral context beyond annotations: it explains the two login modes (permanent via header vs session-only via token), how to trigger the login link, and the distinction of token expiry. Annotations already indicate idempotency and non-read-only, and the description aligns with these while adding meaningful workflow details.
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 paragraph but well-structured, front-loaded with the tool's purpose, then delineating two clear usage paths. Every sentence contributes value, though it could be slightly more streamlined for scanning.
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 lack of an output schema, the description covers the essential flow: how to initiate login, the two authentication methods, and token persistence. It does not detail return values or error cases, but for an auth tool this is adequate and approachable.
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 schema description coverage at 0%, the description fully compensates by explaining the 'token' parameter: it is an optional JWT used for session-only login, and calling with no args returns the login link. This provides complete parameter semantics 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 states the tool's purpose: authenticate the MCP.AI server for IDE agents via a browser login and token exchange. It specifies the resource (auth for MCP.AI) and distinguishes itself from siblings by detailing a unique token-based flow involving config header or session token. This is a specific verb+resource+scope.
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 explicit usage context: when to use the permanent config-header method versus the session-only token method, and how to call with or without the token. It does not explicitly compare against the sibling 'connect' tool, but the guidance is clear enough for an agent to know when to use this tool.
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.
Most platform tools are distinct (bug reporting, version, toolkit state), but authenticate and connect overlap around auth/connection status, and marketplace is a sprawling multi-purpose tool that also covers installation, search, billing, and prompts, making its boundaries fuzzy. The single domain tool, tribunal_trt20_processo_consultar, is clearly unique but is buried among generic platform utilities.
Names mix bare verbs (authenticate, connect), nouns (marketplace), verb_noun underscores (report_bug, show_version), and one Portuguese domain name (tribunal_trt20_processo_consultar) that reverses the typical object-verb order. There is no consistent pattern across the set.
Seven tools is a reasonable number, but six of them are generic MCP platform utilities while only one is relevant to the server's stated purpose of TRT20 process consultation. The count is not extreme, but the scope feels imbalanced for a specialized tribunal server.
For a read-only process consultation use case, the single tribunal tool may be sufficient, but the server provides no supporting domain operations beyond that one query. The impressive breadth of marketplace and platform tools does not compensate for the lack of any additional case-related functionality.