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, the description adds useful behavioral context: the distinction between permanent and session-only connections, how to pass the token, and what happens with no arguments. It does not fully describe the response for a token call, but no annotation contradiction exists.
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?
Two sentences cover the core action, recommended setup, alternative session-only flow, and no-argument behavior with almost no filler. The structure is scannable and 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 a one-optional-parameter auth tool with no output schema and annotations covering safety/idempotence, this description is nearly complete. It covers all call variants and the link retrieval behavior, though it could briefly state what happens after a successful token-based login.
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 coverage is 0%, so the description carries the burden. It explains that token is an optional JWT pasted by the user and that omitting it returns the login link. This is helpful, though it does not fully specify token constraints or the success response.
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 states a specific action: authenticate with MCP.AI by logging in through a browser and using an access token. It is detailed enough to be distinguished from sibling tools like connect or marketplace, even without explicitly naming them.
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 usage paths: configure a permanent Authorization header, pass a token for a session-only login, or call with no args to get the login link. It never explicitly contrasts this with a sibling tool like connect, so it misses the highest bar for when-not-to-use guidance.
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 Plaud-specific tools are clearly distinct, but 'marketplace' is a mega-tool that appears to cover search, invoke, install, subscribe, prompts, and bug reporting — overlapping with connect, toolkit_info, and the standalone report_bug tool. An agent could easily pick the wrong entry point for connection status, installed tools, or feedback.
There is a clean plaud_get_* / plaud_list_* cluster, but the platform tools mix verbs and nouns: authenticate, connect, marketplace, report_bug, show_version, toolkit_info. The naming is readable and the Plaud prefix helps, but the overall pattern is inconsistent.
Eleven tools is a reasonable count and mostly well-scoped for a Plaud integration plus MCP platform management. It is slightly heavy because 'marketplace' bundles many sub-capabilities into one tool while several small utility tools exist separately.
The Plaud retrieval surface covers user, recordings, recording details, transcript, and AI notes, which is sufficient for the main use case of accessing Plaud data. Minor gaps exist around delete/update operations, but recordings are created externally by the hardware, so read-focused coverage is acceptable.