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?
Discloses that calling with no args returns a login link, while providing a token gives session-only authentication. Adds context beyond the idempotentHint annotation by describing the side-effect-free nature of returning a link. Could mention failure cases but overall transparent.
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 compact yet comprehensive, using 'Best' and 'Or' to structure alternatives. Every sentence adds value, and the critical info (login method) is front-loaded.
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 explains the return behavior (get a link) and the two use cases. It lacks explicit error handling details but is sufficiently complete for an agent to invoke correctly.
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?
Schema has 0% description coverage for the 'token' parameter, but the description fully explains it as a JWT access token and clarifies it is optional. Provides concrete examples: '{ token: "<jwt>" }' and 'no args to get the link', making the parameter semantics unmistakable.
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 authenticates the user to the MCP server by logging in via browser and copying a token. It distinguishes from siblings by describing the auth flow for IDE agents, though it doesn't explicitly differentiate from 'connect'.
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 guidance on two usage modes: permanent config header vs session-only token paste, and explains when to call with/without the 'token' argument. Clearly tells the agent when to use this tool and how to handle both scenarios.
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 purposes, but 'authenticate' and 'connect' both deal with authentication state, and 'marketplace' overlaps slightly with 'toolkit_info' in terms of discovering vs. viewing tools. These pairs could cause initial confusion, though descriptions help.
Names mix English verbs (authenticate, connect, report_bug) with a noun (marketplace) and a Portuguese command (fincen_consultar). There is no consistent verb_noun or noun pattern, making the set feel ad hoc.
With 7 tools, the number is well within the typical range for a platform server. Each tool serves a distinct functional area (auth, status, query, marketplace, bug, version, toolkit), so none feels superfluous.
The platform covers essential operations: authentication, connection status, tool discovery/execution, bug reporting, version info, and toolkit state. The FinCEN-specific side is minimal (one query tool), but the marketplace allows extending coverage, so the surface is reasonably complete.