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 the effects of the tool: using the token for permanent config vs session-only. It does not explicitly mention side effects like token storage, but the annotations (destructiveHint:false, idempotentHint:true) align and the description gives a transparent view of both modes.
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 dense but organized: it starts with the general process, then presents two alternatives. It is not overly verbose, though the phrasing 'Best:' and 'Or' could be streamlined. Overall, it is efficient.
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 description is complete for the tool's function: it explains the two usage scenarios, what each call does (returns link vs authenticates), and the permanent vs session difference. No output schema is needed since the behavior is fully described.
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 single parameter 'token' is fully explained: it is the JWT to paste for session login, and if omitted, the tool returns the login link. The description clarifies both call modes clearly.
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: authentication for MCP.AI for IDE agents. It explains the two methods of using the token (permanent config addition or session-only) and the two call variations (with or without token).
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 instructions: log in via browser, copy token, then either add to config for permanent use or paste for session-only. It also clarifies when to call with token vs without args to get the login link.
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.
Multiple tools have unclear boundaries: connect and toolkit_info both describe connection/status information, and marketplace is a catch-all that can invoke one-off tools, complicating the distinction from the direct CND consultation tool. The only clearly unique domain tool is pref_ba_juazeiro_cnd_consultar, but the generic helpers overlap with each other.
Tool names mix bare verbs like connect and report_bug with noun-style names like marketplace and toolkit_info, and the Portuguese-specific pref_ba_juazeiro_cnd_consultar follows a different convention. There is no consistent verb_noun or domain pattern across the set.
Seven tools is a reasonable count for a platform-support surface, so the size is not inherently bloated. However, only one tool directly serves the apparent CND-focused purpose, with the rest being generic platform/management helpers, creating a borderline scope mismatch.
The CND domain is essentially a single consult operation, and pref_ba_juazeiro_cnd_consultar covers that core workflow. The supporting tools provide enough auth/connection and error-reporting coverage, though a dedicated provider-specific workflow beyond that would be clearer.