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 reveals important behavior beyond annotations: no-args returns a login link, pasting a JWT creates a session-only login, and config headers create a permanent non-expiring connection. These details are not captured by the annotations and add meaningful context.
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 appropriately sized and front-loaded with the purpose, then expands into the two authentication options. Every sentence contributes actionable information with no filler or redundancy.
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 one-optional-parameter auth tool with no output schema, this description is complete. It covers the permanent path, session path, token parameter semantics, and no-arg behavior, leaving no important usage gap.
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 coverage is 0%, but the description fully compensates by explaining that the single `token` parameter is a JWT access token and how to use it. It also specifies the no-argument behavior, which is not evident from the schema.
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 to MCP.AI by logging in and obtaining an access token. It distinguishes itself by explaining both permanent config-based auth and session-only token auth, which goes beyond the generic tool name.
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: add the token as an Authorization header for permanent access, paste it for session-only login, or call with no args to get a login link. It does not explicitly contrast with sibling tools like connect, so it stops short of full alternative-tool 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 tools are a mix of platform-level utilities (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) and one domain-specific tool (sefaz_df_iss_consultar). The platform tools have overlapping purposes: authenticate and connect both deal with connection/auth status, and marketplace and toolkit_info both describe available tools/MCPs. The single domain tool is clearly distinct, but the platform tools blur boundaries.
Naming is inconsistent: some tools use snake_case (sefaz_df_iss_consultar), some use lowercase single words (connect, marketplace), and some use underscore-separated phrases (report_bug, show_version, toolkit_info). There is no consistent verb_noun pattern, and the domain tool's name is verbose and not aligned with the others.
7 tools is a reasonable count, but the server appears to be a platform wrapper with only one actual domain tool (SEFAZ DF ISS). The other six are generic platform utilities that could be considered out of scope for a domain-specific server, making the count feel padded rather than focused.
For a server named 'SEFAZ DF: ISS', the only domain operation is a single consult (query) tool. There is no support for other ISS-related operations (e.g., issuing, updating, or managing documents), and the rest of the tools are unrelated platform management functions. The domain surface is severely incomplete.