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 behavioral context beyond the annotations: token can be permanently tied to the server config or only used for a session, and calling with no arguments returns the login link. No contradiction with idempotentHint or other annotations.
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 well-structured: it states the flow, the best long-lived option, and the session-only alternative. Every sentence adds relevant information without significant 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?
The description clearly covers the main auth scenarios: no args for a link, token for session login, and config for permanent auth. There is no output schema, and it could more explicitly say return value/error behavior, but the core operation is complete enough for an agent.
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 0% description coverage for the token parameter, but the description compensates by explaining it is the JWT access token the user pastes, and by describing call shapes like { token: "<jwt>" } or empty args.
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 identifies the tool as an authentication mechanism for MCP.AI/: it tells the agent to have the user log in, copy the access token, and either configure it or pass it to the tool. It distinguishes itself from unrelated sibling tools by focusing purely on auth flows.
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 explicit guidance on when to pass a token vs. call with no arguments, and contrasts long-lived config auth from session-only auth. It does not explicitly mention sibling alternatives, but the usage modes are 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.
The captcha_solve_* tools are clearly distinct by captcha type, and captcha_get_result is separate. However, authenticate, connect, and toolkit_info overlap in purpose (auth/status), and marketplace bundles a huge range of unrelated functionality, creating ambiguity about which tool to use for platform management.
The captcha tools follow a consistent captcha_solve_<type> pattern, but the rest of the set uses bare verbs (connect, authenticate, marketplace) or inconsistent forms (toolkit_info, show_version). Mixing prefixed captcha tools with generic platform tools makes the naming scheme disjointed.
At 12 tools the raw count is reasonable, but the server is named 'Captcha Solver' yet includes a large platform/marketplace tool and several generic management tools. The captcha-specific scope is small (7 tools), while the extra tools feel bolted on and dilute the server's purpose.
The captcha solving surface covers main types (image, hCaptcha, reCAPTCHA v2/v3, Turnstile) plus result retrieval, which is decent. However, there is no dedicated balance/credit check or captcha task listing, and the broad marketplace/toolkit functionality makes it unclear what domains the server is supposed to fully cover.