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?
Adds context beyond annotations by describing the two login modes (permanent vs session) and the browser flow. However, it does not mention error handling or what happens on invalid token, though idempotentHint suggests repeat calls are safe. The description covers essential side effects without being exhaustive.
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?
Description is compact yet information-dense. Leads with purpose, then clearly delineates two methods ('Best:' and 'Or'). No fluff, every sentence serves the user.
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 complexity (two authentication paths, optional param, no output schema), the description fully explains both modes, the user interaction (browser login), and how to invoke with or without token. Ample for correct usage.
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 has 0% coverage for the 'token' parameter, but the description compensates well: it explains the token is a JWT used for session login, and gives the exact call format. It lacks details on token format validation or expiration, but is sufficient for usage.
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?
Clearly states the tool's purpose: authentication for MCP.AI IDE agents, with explicit instructions for browser login and token usage. It distinguishes from siblings like 'connect' and 'marketplace', which serve different functions.
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?
Provides explicit when-to-use guidance: 'Best: add it to this server's config as a header' for permanent login, or 'paste it here for a session-only login'. Also instructs exact call patterns: with token after user pastes, or no args to get link. No alternatives are needed as no sibling performs authentication.
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 are generic platform tools (authenticate, connect, marketplace, etc.) rather than domain-specific, and 'marketplace' explicitly mentions CPF queries which could be confused with the BCB consult tool. 'connect' and 'toolkit_info' also overlap in providing status information.
The naming is highly inconsistent: most tools use English imperative verbs (authenticate, connect, report_bug, show_version) or nouns (marketplace, toolkit_info), while the only domain-specific tool uses a Portuguese noun phrase with underscore format (bcb_valores_receber_consultar). No clear pattern across the set.
Seven tools is not inherently excessive, but six of them are generic platform management features unrelated to the server's stated purpose of accessing BCB values. The count is inflated with irrelevant tools, making the server poorly scoped for its intended domain.
From a domain perspective, the single BCB consult tool covers the core need for checking 'valores a receber'. However, there is no option for related operations (e.g., scheduling, detailed reports), and the included generic tools do not contribute to domain completeness. Overall, the surface is minimal but not severely incomplete for a simple query.