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 (idempotent, non-destructive), the description discloses that passing a token creates a session-only login, omitting it returns the link, and the recommended config approach gives a non-expiring connection. It does not detail failure behavior or whether an existing session is replaced, but the added context exceeds what the annotations provide.
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 relatively compact but awkwardly worded ('log in in the browser') and mixes setup instructions with tool-call semantics in one run-on passage. It is not excessively long, but readability and structure could be improved.
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 two usage modes and the optional token are covered, which is sufficient for basic invocation. However, with no output schema, the description never states what the tool returns on success or failure, and it leaves unclear how the agent should present the login-link flow to the user.
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?
Even though schema coverage is 0%, the description compensates by explaining the single token parameter: it is a JWT, optional, and omitting it triggers the no-args link flow. It could add more detail about token format or expiry, but for one parameter the semantics are well covered.
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 identifies the tool as authentication for MCP.AI with IDE agents and explains the two invocation modes (with a JWT token or with no arguments). It is clear about the resource, but it never explicitly uses a verb like 'authenticate' and does not differentiate itself from sibling tools such as 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?
It gives concrete when-to-use guidance: use the config header for a permanent connection or paste the token for a session-only login, and call with no args to get the login link. It does not mention alternatives/exclusions relative to sibling tools, but the intended usage context is clear.
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.
marketplace and search_tools both cover catalog search, describe, and invoke, making their boundaries unclear. connect and toolkit_info also overlap on reporting connection status, so an agent could easily select the wrong tool for the same task.
All names use lowercase snake_case, but the patterns vary: single-word verbs (authenticate, connect), a noun (marketplace), and compound nouns (toolkit_info). There is no consistent verb_noun convention, though the names remain reasonably readable.
Seven tools is a reasonable size for an MCP platform-management server, and most tools cover distinct operational areas. However, marketplace and search_tools overlap significantly, so the count could be trimmed without losing functionality.
The set covers authentication, connection status, catalog search and execution, toolkit state, version info, and bug reporting, which supports the core platform workflows. The main weakness is that install/uninstall/billing operations are buried inside the marketplace tool description rather than exposed as first-class tools.