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 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds transparency beyond the annotations by explaining the persistence of the header connection ('permanent, non-expiring') versus session-only token login. It also describes the behavior of getting a link with no args. This enriches the provided hints without contradiction.
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 concise and information-dense, using two sentences to cover configuration, session login, and no-arg behavior. While it reads as a run-on, each clause adds unique value. Slight restructuring into steps could improve scannability, but it remains efficient.
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 essential workflow and edge cases (no args, token supplied). It doesn't mention return values, but in the absence of an output schema, that is not strictly required. The tool is simple enough that the description feels complete.
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 provides no description for the token parameter, but the description fully explains it: a JWT pasted by the user, and that omitting it yields a login link. This completely compensates for the 0% schema coverage, giving the agent all necessary semantics.
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: authenticating IDE agents (e.g., Cursor) via login flow. It specifies the resource and the action (obtaining an access token) and differentiates itself from siblings like connect or marketplace, which are unrelated. The scope is precise.
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 usage instructions: call with no args to get a link, or with a token for session-only login. It also contrasts two methods (persistent header vs. session token). However, it doesn't explicitly state when to choose this tool over alternatives or when not to use it, so it falls just short of a 5.
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.
There is significant overlap: marketplace internally includes report_bug, connection status, and install management, duplicating the dedicated report_bug, connect, and toolkit_info tools. Authenticate and connect are also related to authentication/connection, making boundaries unclear.
Tool names follow no consistent pattern: single verbs (authenticate, connect), nouns (marketplace, toolkit_info), verb_noun (report_bug, show_version), and a long domain-specific snake_case (sefaz_rr_nfce_consultar). This makes the set feel chaotic and unpredictable.
Although 7 tools is a reasonable count, the server is named for SEFAZ NFC-e yet only 1 tool serves that domain. The other 6 are generic platform management tools (auth, connection, marketplace, version) that are out of place in a domain-specific server.
The domain surface is severely incomplete: a single NFC-e consultation tool, with no support for searching, listing, canceling, or other common NFC-e operations. Meanwhile, platform management is over-covered, with multiple overlapping tools and marketplace's broad feature set.