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?
Annotations already provide idempotentHint=true, readOnlyHint=false, and destructiveHint=false. The description adds behavioral context about permanent vs session-only authentication and explains what happens when called with or without a token. This goes beyond the annotations without contradicting them.
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 slightly run-on but front-loaded with the key purpose ('log in in the browser, copy the access token') and each sentence contributes to usage or behavior. It's dense but not overly long, earning a 4.
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 tool with one optional parameter and no output schema, the description explains both invocation modes and the token lifecycle. It doesn't detail return values beyond 'get the link', but this is sufficient for the tool's simplicity.
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 and only one optional 'token' parameter, the description compensates by clarifying that token is a JWT for session-only login, and that calling with no args returns a link. This gives the parameter meaning beyond the bare string type.
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: 'log in in the browser, copy the access token' for MCP.AI IDE agents. It distinguishes itself from siblings by focusing specifically on authentication and token handling, with a clear verb ('log in') and resource ('MCP.AI').
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 provides explicit usage guidance with two clear options: adding a bearer token to server config for a permanent connection, or pasting a JWT for session-only login. It also instructs calling with no args to get the link. However, it does not explicitly exclude alternatives like the 'connect' sibling, so it's not a full 5.
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 clear, distinct purposes: authentication, connection status, bug reporting, version info, and toolkit state are all separate concerns. However, `connect` and `toolkit_info` overlap somewhat in reporting connection status, and `marketplace` is a large catch-all that could be confused with a standalone platform tool.
Tool names follow no consistent pattern. Some are single verbs (`authenticate`, `connect`), some are verb_noun (`report_bug`, `show_version`), one is a noun (`marketplace`), one is noun_info (`toolkit_info`), and one mixes English with Portuguese (`fbi_most_wanted_consultar`). This inconsistency makes the set feel like a random collection rather than a coherent API.
Seven tools is a reasonable count for a general utility server, but the server is named 'FBI Most Wanted' and only one tool is domain-specific. The other six are platform administration tools that do not relate to the stated purpose, making the scope confusing and the count feel inflated for a specialized server.
For the FBI Most Wanted domain, only a single lookup operation is provided, lacking features like listing all wanted persons, retrieving details, or batch searching. The platform utilities cover metadata and lifecycle operations, but there are notable gaps in the domain-specific functionality that would require agents to rely on the generic `marketplace` for deeper coverage.