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 adds context beyond annotations: it explains the two authentication modes (permanent vs session), the return of a link, and the optional token parameter. It doesn't contradict the idempotent and non-destructive hints, but it omits error handling details, so it doesn't fully cover all behavioral aspects.
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 three concise sentences, front-loaded with purpose and context, followed by two clear usage modes. Every sentence provides essential information without redundancy.
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 authentication tool with one optional parameter and no output schema, the description adequately covers the workflow, return behavior, and integration options. It is complete given the tool's complexity and available annotations.
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, the description fully compensates by explaining the 'token' parameter as a JWT and clarifying the behavior when omitted (returns a login link). This adds meaning beyond the bare schema definition.
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: authenticating the user via browser login and token exchange. It distinguishes itself from siblings like 'connect' by explicitly focusing on authentication and token handling, making the tool's specific role obvious.
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 gives explicit usage alternatives: adding the token to config for permanent access, pasting a JWT for session-only login, or calling with no arguments to obtain a link. It also indicates the best practice, which clearly differentiates when to use each approach.
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.
The set has major overlap: `marketplace` and `search_tools` both offer search/describe/invoke catalog actions, making it unclear which to call. `report_bug` is also called out as a capability inside `marketplace`, blurring whether that tool is the action or the top-level one.
All names are lowercase with underscores, but they mix verb-oriented names (`authenticate`, `connect`, `report_bug`) with noun-oriented names (`marketplace`, `search_tools`) and no consistent verb_noun pattern. `show_version` and `toolkit_info` are similarly status-like but follow different naming styles.
Seven tools is within a reasonable range and the count itself is not problematic. However, the `marketplace` tool is overloaded with many sub-capabilities and `search_tools` duplicates part of it, so the effective scope feels less clean than the raw count suggests.
The main workflows are covered: authentication, connection status, catalog search, account/toolkit state, and bug reporting. Missing pieces like an obvious way to uninstall/disconnect or list callable tools are hidden inside `marketplace`, but these are workable gaps rather than fatal ones.