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?
Annotations already indicate idempotent and non-destructive side effects. The description adds useful context about the two modes (session vs permanent config), how tokens are used, and that calling with no args returns a login link. This enriches beyond annotation signals without contradicting them.
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 a single run-on sentence but front-loads the core purpose and packs essential guidance (browser login, token, two alternatives). It is somewhat dense but every clause adds value, only slightly compromising readability.
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?
Given there is no output schema, the description mentions the return behavior (getting a link with no args) but does not detail success/failure responses for token submission. It is sufficiently complete for a simple auth tool, with annotations covering side-effect safety.
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 coverage, the description compensates by explaining the 'token' parameter as a JWT pasted from the browser, and clarifies it is optional (no args gets the link). It does not over-specify formatting but provides enough meaning for correct invocation.
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 within IDE agents, with a specific flow (browser login, token copy/paste). It distinguishes itself from siblings like 'connect' by focusing on login/token exchange, making its purpose unambiguous.
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 explicitly explains when to use the tool (for login) and provides two distinct invocation patterns: passing a token for session-only login, or calling with no args to obtain a login link. It also recommends the preferred permanent configuration method, giving clear context for both scenarios.
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.
Multiple platform utility tools overlap: authenticate, connect, and toolkit_info all deal with connection/auth state, while marketplace bundles search, invoke, install, billing, and prompt library functions into one tool. The only domain-specific tool, bpc_consultar, is clearly distinct but the rest have blurred boundaries.
Tool names follow no consistent pattern: some are bare verbs (authenticate, connect), some are noun phrases (marketplace, toolkit_info), and the domain tool uses an underscore-prefixed convention (bpc_consultar). Mixed styles make it hard to predict tool names.
Seven tools is a reasonable number, but the server is ostensibly for BPC consultation, and only one tool addresses that domain. The rest are generic platform utilities that seem bolted on, making the set feel bloated for the stated purpose and under-delivering on the core domain.
For a BPC server, the surface is severely incomplete: only one consult operation exists, with no support for other related actions. The platform utility tools don't fill this gap; they serve a different purpose entirely, leaving the BPC workflow with a dead end.