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, readOnlyHint: false), the description discloses behavioral nuances: the difference between permanent non-expiring access via config versus session-only login via token, and the no-args behavior returning a login link. This adds valuable context about side effects and persistence.
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 fairly compact but information-dense, covering all usage modes in three sentences. It's not overly verbose, though the structure could be improved slightly with bullet points for clarity. Every sentence serves a purpose.
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 an auth tool with no output schema, the description adequately explains the primary behaviors: getting a link, passing a token, and the permanent vs. session distinction. It does not describe return values explicitly, but the link output is implied for no-args calls, and the overall flow is sufficiently complete.
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 has one optional 'token' parameter with zero description. The description explicitly explains the token's purpose (JWT to paste) and the no-args case (returns link), fully compensating for the schema's lack of detail. This is strong parameter documentation.
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 this tool handles authentication for MCP.AI in IDE agents, specifying the login flow via browser and token extraction. It distinguishes itself from siblings by focusing on the OAuth token exchange, though it does not explicitly contrast with the 'connect' sibling.
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 clear context on how to use the tool—either by configuring a permanent Bearer header or passing a token for session-only login, and using no args to get a link. However, it does not explicitly state when to choose this tool over alternatives like 'connect'.
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 have distinct purposes: authenticate handles login, connect shows connection status, marketplace handles discovery and invocation, report_bug sends feedback, show_version displays versions, toolkit_info shows installed MCPs. The single domain tool caf_agricultura_pj_consultar is clearly separate. Minor overlap exists between connect and toolkit_info (both touch connection status), but descriptions clarify their roles.
Naming is inconsistent: some tools are bare verbs (authenticate, connect, marketplace), some are snake_case verb_noun (report_bug, show_version, toolkit_info), and one is a long Portuguese domain-specific name (caf_agricultura_pj_consultar). There is no unified pattern or verb style across the set.
Seven tools is a reasonable number for a general platform toolkit. However, the server name suggests a CAF-specific domain, yet only one tool is actually CAF-related; the rest are generic platform utilities. The count itself is fine, but the scope is slightly mismatched with the server's title.
The platform tooling is fairly complete: authentication, connection status, marketplace search/run, bug reporting, version info, and toolkit state cover common needs. The CAF domain has a single query tool, which may be sufficient for a simple lookup, but lacks any additional operations like batch queries or listing categories. Minor gaps, but no critical dead ends.