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 discloses key behavioral traits beyond annotations, such as the two modes (permanent via config vs session-only token), the fact that the token is a JWT, and the workflow of obtaining a link first then authenticating. However, it doesn't mention error cases or response details, which would add more 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 about 60 words but packs in all essential information: purpose, best practice, alternative, and exact call patterns. It is well-structured with clear separation of options, and every sentence adds value without 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?
The tool is simple with one optional parameter and no output schema. The description covers the main workflow and user scenarios well, but doesn't explicitly state what the tool returns (e.g., a link or success message). Given the tool's simplicity, this is a minor 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?
The input schema has only a 'token' property with no description, but the description thoroughly explains its meaning and usage: it's an optional JWT for session-only login, and omitting it returns a login 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 explicitly states the tool's purpose: authentication for MCP.AI in IDE agents, detailing the browser login and token acquisition flow. It clearly distinguishes from sibling tools by focusing on token handling, while other tools like connect or marketplace have different scopes.
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 provides explicit when-to-use guidance: it recommends adding the token to the server config for a permanent connection, or pasting it for session-only login. It also gives invocation patterns: call with no args to get a link, or with a token after pasting, leaving no ambiguity about usage.
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.
Most tools have distinct purposes, but marketplace bundles many sub-actions (search, describe, invoke, install, subscribe, etc.) into one tool, and connect/toolkit_info both report connection/status information, creating some boundary ambiguity.
Naming is mixed: simple verbs (authenticate, connect), verb_noun patterns (show_version, report_bug, toolkit_info), a single noun (marketplace), and a domain-specific compound (nfe_inutilizacao_consultar) do not follow a consistent convention, though names remain readable.
With 7 tools, the count is within a normal range, but only one tool (nfe_inutilizacao_consultar) relates to the server's stated purpose of NFe inutilizações. The other six are generic platform utilities that inflate the count for a domain-specific server.
The domain surface is severely limited: a single consult operation (nfe_inutilizacao_consultar) with no additional NFe-related operations such as listing, filtering, or exporting. The platform tools do not address the domain, leaving agents with only one tool for all NFe tasks.