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 non-read-only, idempotent, non-destructive. The description adds behavioral context: it initiates a login, supports a non-expiring config approach vs a session-only approach, and expects a JWT. No contradiction; it reasonably discloses the main state-changing nature of the 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 compact and front-loaded, delivering the essential workflow in a few sentences. Slight redundancy/preamble ('MCP.AI for IDE agents') and the awkward phrase 'log in in the browser' prevent a perfect score.
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 covers the primary use cases, token sourcing, and two authentication paths. It does not mention the response after a successful token submission, but this is a minor gap for such a simple auth flow.
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 defines an optional string 'token' with no description. The description compensates well by explaining the token's format, how to pass it, and the no-args behavior for obtaining the link.
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 explains what the tool does: authenticates to MCP.AI via a browser-generated token, with two modes (config header or session token). It does not explicitly distinguish itself from sibling tools like 'connect', but the resource and action are specific enough.
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?
Provides clear guidance on when to use the permanent config-header approach versus the session-only token approach, but does not contrast with sibling tools or state when not to use this tool. The context is usable but lacks explicit alternatives/exclusions.
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 dedicated query tool and version/status tools are clear, but the set has fuzzy boundaries around connection and catalog inspection: `connect` and `toolkit_info` both expose connection state, and `marketplace` overlaps with the standalone `report_bug` and `toolkit_info` tools through its many sub-actions. The descriptions help somewhat, but an agent could easily pick the wrong administrative tool.
There is no predictable naming pattern: bare verbs like `authenticate` and `connect`, nouns like `marketplace`, compound nouns like `toolkit_info`, and verb_noun names like `report_bug` and `show_version` are mixed together. The single domain tool `tribunal_trt15_processo_consultar` follows a completely different, long Portuguese naming convention.
Seven tools is a reasonable size and fits comfortably within a typical MCP server scope. The split is top-heavy, however, because only one tool actually serves the TRT15 process-consultation purpose while the others are generic platform/infrastructure tools.
The read-only consultation use case is essentially covered by the tribunal-specific query tool, and platform needs such as authentication, connection status, marketplace access, and bug reporting are present. The main gaps are minor: there is no TRT15-specific history, batch lookup, or additional process-related variant, but the core workflow is not blocked.