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 discloses important behavioral traits: the permanence of the config-based approach versus the session-only nature of passing a token, and the fact that calling with no args returns a link. This goes beyond the annotations (readOnlyHint=false, idempotentHint=true) by explaining the side effects of each usage mode, though it does not explicitly mention side effects like logging out or token expiration.
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 somewhat verbose but well-organized with 'Best:' and 'Or' to separate the two modes. It contains minor redundancy (e.g., 'log in in the browser') but overall conveys essential information without excessive fluff. It could be trimmed slightly but remains clear and readable.
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 no output schema, the description explains the expected behavior: it returns a link when called with no args, and likely completes authentication when a token is provided. It gives enough context for an agent to understand the tool's functionality and prerequisites, though it doesn't explicitly state the return value for the token-based call.
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 only parameter 'token' is explained in the description: it is used for session-only login when passed. The description clarifies that the token is a JWT and how it differs from the config approach. Although the schema has no description, the tool description fully compensates.
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 explains the tool's purpose: authentication for IDE agents. It details the login flow, token acquisition, and two modes of usage (permanent via config header, session via token). This is distinct from sibling tools like image generation or subscription, leaving no ambiguity.
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 explicitly provides two usage scenarios: 'Best: add it to this server's config...' for permanent connection, and 'Or paste it here...' for session-only login. It also mentions calling with no args to get the login link. This gives clear, actionable guidance on when and how to invoke the tool.
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 clearly distinct purposes: authenticate handles login, connect checks status, codex_image_generate creates images, and marketplace is a meta-catalog. There is minor overlap between connect and codex_image_subscription both showing status, but detailed descriptions mitigate confusion. Marketplace is broad but self-contained.
Tool names follow mixed conventions: verb-only (authenticate, connect), verb_noun (report_bug, show_version), prefixed with codex_image_ (generate, subscription), and noun-only (marketplace, toolkit_info). No consistent pattern across the set, making it hard to predict tool names.
With 8 tools, the count is within the typical 3-15 range and not excessive. The scope is broad (image generation plus platform utilities), but each tool has a defined role, so the number feels justified for a meta-toolkit server.
For the image generation domain, only generate and subscription are present, lacking image history or management features. However, the marketplace tool can dynamically fill gaps by invoking other MCPs, and the core generate workflow is covered. Platform utilities like reporting and versioning are complete.