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 valuable context beyond annotations: explains the two invocation modes (with/without token), the permanent vs session distinction, and that the token is a JWT. Annotations already cover idempotency and non-destructive nature, and the description aligns without contradictions.
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 somewhat long but well-structured, leading with the purpose and then presenting clear options. Each sentence contributes useful information, with no fluff or repetition of schema details.
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 minimal schema and no output schema, the description covers all essential aspects: how to authenticate, the two usage modes, and the intended environment. It lacks explicit failure behavior but remains complete for typical use.
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 only an optional 'token' with no description, so the description carries full burden. It explains that 'token' is a JWT for session-only login, and also covers the no-args call to obtain the link. This fully compensates for the 0% schema 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 states the tool's purpose: authentication for MCP.AI in IDE agents. It specifies the exact actions (log in, get token, call with token or no args) and differentiates from siblings like 'connect' by focusing on token-based auth.
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 explicit usage scenarios: permanent via config header, session-only via token, and no-args to get link. It doesn't directly compare with alternatives but gives sufficient guidance for correct invocation.
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 serve distinct purposes: authentication, connection status, marketplace operations, bug reporting, version display, toolkit info, and a single SEFAZ consultation. There is minor overlap between connect and toolkit_info (both show connection state), but generally an agent can distinguish them. The mix of platform management tools with a domain-specific tool is confusing, though each tool's role is clear.
Naming conventions are inconsistent: some tools use single words (authenticate, connect, marketplace), others use underscores (report_bug, show_version, toolkit_info), and the domain-specific tool follows a long, descriptive snake_case pattern (sefaz_se_nfce_consultar). Verb-noun structure is not consistent, and there is no clear naming hierarchy.
Seven tools is within a reasonable range, but the server is named for SEFAZ SE NFC-e while only one tool relates to that domain. The rest are generic platform utilities. This makes the count feel inflated relative to the advertised purpose, though not extreme.
For the stated domain of SEFAZ SE NFC-e, only a single consult tool exists. There is no support for other lifecycle operations (e.g., listing, updating, canceling) nor any additional SEFAZ-related functionality. The platform tools do not fill this gap. The surface is severely incomplete for its apparent purpose.