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?
Beyond the annotations (idempotentHint true, destructiveHint false), the description adds important behavioral context: the distinction between permanent non-expiring connections and session-only logins, and that no-args returns a link. This meaningfully enriches the annotation-only signal without contradicting it.
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?
Three focused sentences effectively cover purpose, best-practice configuration, and invocation alternatives. The description is front-loaded with the key action and avoids fluff or repetition.
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 low-complexity tool with one optional parameter and no output schema, the description provides complete invocation context: what to do with a token, how to get a link, and the permanent vs session distinction. No critical behavioral gaps remain.
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?
With 0% schema description coverage, the description fully compensates by explaining the single optional token parameter: it should be a pasted JWT for session login, and its absence triggers link generation. This gives the agent actionable semantics beyond the bare 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: authenticate to MCP.AI for IDE agents by producing a browser login link or accepting a pasted JWT token. It goes beyond the name by specifying the exact resource and workflow, and it is clearly distinct from sibling tools like connect or report_bug.
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?
It provides explicit usage guidance: add the token as a permanent Authorization header in config, or pass { token } for a session-only login, or call with no args to get the login link. This tells the agent exactly when to use which mode, including a recommended best practice.
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 marketplace tool is a catch-all that includes searching, invoking, and installing MCPs, which overlaps with the domain-specific mpt_es_cnf_consultar (it even mentions 'consulta um CPF'). Additionally, authenticate and connect both deal with authentication/connection flows, creating ambiguity. The detailed descriptions help, but the functional overlap is significant.
Naming is a mix of single verbs (authenticate, connect), nouns (marketplace), and snake_case verb phrases (report_bug, show_version, toolkit_info). The domain-specific mpt_es_cnf_consultar follows a completely different pattern (abbreviated, underscores) making it stand out unpredictably. No consistent verb-object or noun-based convention is maintained.
With 7 tools, the count is well within the ideal 3-15 range for a focused server. Each tool covers a clear functional area, even if some are overloaded (e.g., marketplace). No concern about bloat or triviality.
For a certificate lookup service, mpt_es_cnf_consultar covers the core query, and the platform tools (authenticate, connect, marketplace) provide surrounding infrastructure. However, the server bundles a broad marketplace feature set that seems orthogonal to the certificate domain, suggesting the domain may be under-served (e.g., no status/history tools). The platform aspects are well-covered, but the apparent primary use case (certificate lookup) is implemented as a single endpoint with no additional related operations.