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 already flag idempotent and non-destructive, so safety is covered. The description adds behavioral context by explaining the two modes (permanent via config, session via token) and the no-arg link retrieval. It does not detail session expiration or side effects, but is consistent with annotations and gives useful beyond-schema information.
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 moderately long but every sentence serves a purpose, covering context, permanent token setup, session login, and argument handling. It is front-loaded with the tool's target audience, though the formatting could be slightly more compact.
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 an authentication tool with no output schema, the description gives enough context: how to authenticate (browser), token format (JWT), two usage modes, and the no-arg behavior. It does not mention response details or error cases, but these are not critical given the annotations and schema.
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 schema has one undocumented optional string parameter `token`, but the description explains it fully: `token` should be a JWT pasted by the user, and calling with no args returns a login link. This completely compensates for the 0% schema description coverage.
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 the tool handles authentication, explaining how to obtain and use access tokens for IDE agents. It distinguishes itself from siblings like connect or marketplace by focusing on login/token exchange, though the exact verb 'authenticate' is implied rather than explicitly stated.
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?
It provides clear usage guidance: use this tool for session-only login or to get a login link, and the 'best' alternative is to add a permanent token to the server config. It does not explicitly compare to sibling tools but offers a practical when-to-use versus when-to-use-config distinction.
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.
Tools have mostly distinct purposes: authentication, status, marketplace search/invoke, bug reporting, a specific query, version info, and toolkit info. Some overlap exists between connect and toolkit_info (both report connection state), but overall the boundaries are clear enough.
Naming is inconsistent: single verbs (authenticate, connect) mix with descriptive names (marketplace, report_bug, show_version, toolkit_info), and the domain-specific tool uses a long Portuguese name. No uniform verb_noun or camelCase pattern is followed.
With 7 tools, the count is within the typical 3-15 range. The server bundles platform management with a single domain tool, which is slightly unusual but still reasonable given the dual purpose.
For its stated purpose (SEFAZ PR certificate query), the single consult tool covers the main need, and platform tools comprehensively manage MCP marketplace operations. Minor gaps exist (e.g., no explicit certificate history or financial operations), but core workflows are supported.