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?
Beyond the annotations (idempotent, non-destructive), the description explains behavioral aspects: whether the token is stored permanently (config) or session-only, and that calling with no args returns a link. It doesn't contradict annotations but adds useful nuance about session persistence and configuration alternatives.
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 but packs essential information: how to authenticate via browser, the token parameter, and the permanent vs session distinction. Slightly long but every sentence carries functional value.
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 simple auth tool with one optional parameter, the description fully covers behavior (link generation, token usage) and context (IDE agents). It doesn't describe return format, but no output schema exists to contradict it, so this is adequate.
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?
Schema provides no description for the 'token' parameter. The description fully explains its purpose: an optional JWT to paste for session authentication, or omit to obtain the browser link. This gives complete meaning beyond the schema, compensating for zero 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: to authenticate by either copying an access token from a browser or providing one directly via the 'token' parameter. It distinguishes itself from sibling tools (e.g., connect, show_version) by being the authentication entry point, with specific verbs like 'log in' and 'paste'.
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?
Explicitly describes when to use it: 'Best: add it to this server's config... Or paste it here...' and explains the two invocation modes (no args to get link, or with token). It also contrasts with the recommended permanent config method, giving clear usage guidance.
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 set mixes platform-level tools (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) with a single domain tool (sefaz_df_nfce_consultar). The platform tools have overlapping purposes: authenticate and connect both deal with connection status, and marketplace's invoke/install/list_tools/subscribe/cancel overlap with toolkit_info's reporting of installed MCPs. An agent could easily confuse which tool to call for connection vs. catalog vs. execution.
Naming is inconsistent: platform tools use generic verbs (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) with no consistent pattern, while the domain tool uses a snake_case Portuguese name (sefaz_df_nfce_consultar). The mix of English generic verbs and a Portuguese domain-specific name breaks any predictable convention.
7 tools is a reasonable count, but the scope is muddled: 6 tools are for the MCP platform itself and only 1 is for the actual SEFAZ DF NFC-e domain. The server name suggests a domain-specific service, yet the tool surface is dominated by platform management, making the count feel misaligned with the stated purpose.
For the SEFAZ DF NFC-e domain, the surface is severely incomplete: only one consultation tool exists, with no support for other NFC-e operations (e.g., issuance, cancellation, status checks, or batch queries). The platform tools are comprehensive for managing MCPs, but that doesn't cover the domain the server claims to serve.