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 goes beyond annotations by explaining the side effects of authentication, such as establishing a 'permanent, non-expiring connection' or a 'session-only login'. It also clarifies the behavior when called with no arguments versus with a token, which aligns with the idempotent annotation 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 somewhat verbose and mixes introductory context with instructions, but it does follow a logical structure: first explaining the login flow, then detailing the 'Best' (permanent) and 'Or' (session) alternatives. It could be tightened, but the organization is functional.
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?
Given the tool's simplicity and lack of output schema, the description covers the essential context: purpose, usage steps, parameter meaning, and behavioral implications. It does not address error handling or edge cases, but for an authentication tool, this level of detail is sufficient.
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 description provides meaningful context for the 'token' parameter, specifying it is a JWT that the user pastes after logging in. It also explains the alternative of calling with no arguments to receive a link, effectively compensating for the lack of schema-level parameter description.
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 of authenticating the user, providing two distinct methods (permanent config or session token). It uses action-oriented language like 'log in', 'copy', and 'add', making the intent unambiguous. While it doesn't explicitly compare to sibling tools, the intended function is evident.
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 offers detailed step-by-step instructions on how to use the tool, including both permanent and session-based approaches. However, it does not explicitly state when to choose this tool over others or provide exclusion criteria. It implies usage by explaining the flow but lacks comparative 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.
anp_postos_consultar, report_bug, and show_version have clearly distinct roles, but marketplace is a broad multi-purpose tool that overlaps with connect, toolkit_info, and authenticate for status, auth, and catalog concerns. An agent could reasonably misfile a request between marketplace, connect, and toolkit_info.
The names mix bare verbs (authenticate, connect), nouns (marketplace), snake_case verb_noun (report_bug, show_version), noun_noun (toolkit_info), and a Portuguese object-verb name (anp_postos_consultar). There is no consistent naming convention across the set.
Seven tools is a reasonable size and does not feel bloated. However, six of the seven are generic platform utilities that could belong to any server, leaving only one tool actually tied to the 'ANP: Postos' domain.
Platform concerns like authentication, connection status, marketplace discovery, feedback, versioning, and toolkit state are well covered. The ANP/Postos domain itself is represented by a single opaque consult tool with no visible list, filter, detail, or search operations, which is a notable gap for a domain-specific server.