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 explains the side effects of different usage modes (permanent vs session) and the interaction (browser login). It adds context beyond the annotations (idempotent, non-destructive), though it doesn't state outcomes or failure cases explicitly.
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 relatively concise but includes a slightly verbose intro ('MCP.AI for IDE agents (Cursor, etc.)') and repeats the token concept. The structure with 'Best:' and 'Or' is clear, but could be trimmed slightly without losing information.
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 no output schema, the description covers the main usage scenarios and the expected input. It does not mention return values or success/failure indicators, but for a simple authentication tool, the provided context is sufficient for most agents. Slight gap on what happens after authentication.
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 schema only lists an optional 'token' string with no description. The description clarifies that the token is the authentication token obtained from the browser and explains how its presence/absence changes behavior (session vs. link retrieval). 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 clearly states the tool's purpose is authentication for MCP.AI IDE agents. It outlines the auth flow (browser login, token retrieval) and distinguishes it from siblings by implying it is the sole authentication entry point.
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 usage instructions: add token to config for permanent access, pass token as argument for session, or call with no args to get the login link. This gives clear when-and-how guidance, though it doesn't mention alternatives since none likely exist.
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 individually distinct: authenticate handles login, connect checks status, marketplace manages MCPs, report_bug sends feedback, show_version displays versions, toolkit_info shows state, and cro_df_cadastro_consultar performs the domain lookup. No two tools clearly overlap in purpose, though the mix of platform utilities and a domain operation makes the set heterogeneous.
Naming is highly inconsistent: some tools use single verbs (authenticate, connect, marketplace), others use verb_noun (report_bug, show_version, toolkit_info), and the only domain tool uses a snake_case Portuguese name (cro_df_cadastro_consultar). There is no consistent pattern across the set.
Seven tools is a reasonable number, but only one (cro_df_cadastro_consultar) relates to the server's stated purpose of dental council registration. The other six are generic MCP platform utilities that belong to a platform-level toolkit, making the count misleading and inflated for the intended domain.
For the domain 'Cadastro' (registration), only a single consultation tool exists, with no create, update, delete, or list operations. The toolset is severely incomplete for the stated purpose, and the remaining tools are unrelated platform utilities, so the domain coverage is essentially absent.