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 annotations (readOnly=false, idempotent=true, destructive=false), the description adds context about browser login and two modes of token usage. However, it doesn't fully disclose side effects like whether it modifies server configuration or only sets a session, leaving some ambiguity about permanent vs session-only behavior.
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 well-structured sentence that conveys all essential information without redundancy, front-loading the purpose and then detailing usage. Every clause earns its place and there is no fluff.
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 the tool's simplicity (one optional parameter, no output schema), the description covers the main use cases and behavior adequately. It explains how to obtain a permanent connection and a session login, and what to do with the token. It doesn't specify return values or error handling, but for an auth tool this is acceptable.
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 description explains the token parameter: it's a JWT for session login, and omitting it returns a login link. This adds meaning beyond the schema (which only defines token as a string without description), clearly covering both required and optional usage.
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: to authenticate MCP.AI for IDE agents by logging in via browser and obtaining an access token. It specifies the verb 'authenticate' and resource 'MCP.AI server access', distinguishing it from sibling tools like 'connect' by focusing on token-based authentication.
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 provides explicit usage guidance: either configure a permanent header or use a session token by passing the token parameter or calling with no args to get a login link. It clearly explains when to use each mode but does not explicitly compare with alternatives or state when not to use 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.
The `marketplace` tool is a multi-action catch-all that duplicates functionality in dedicated tools: it includes report_bug, install/uninstall, list_tools, auth/connect links, and prompt actions. As a result, an agent may struggle to choose between `marketplace` and the standalone `report_bug`, `connect`, or `toolkit_info` tools; only `mpt_mg_cnf_consultar` is clearly distinct.
The names are all lowercase and readable, but they do not follow one pattern: single-word verbs like `authenticate` and `connect` sit alongside snake_case verb_noun names like `report_bug` and `show_version`, plus noun-style names like `marketplace` and `toolkit_info`. The domain tool `mpt_mg_cnf_consultar` also uses an opaque slug rather than a predictable verb_noun structure.
Seven tools is not a large count by itself, but six of them are generic MCP platform utilities while only one serves the server's apparent domain of MPT MG certificate queries. The `marketplace` tool also bundles many sub-actions, so the nominal count understates the real surface and overstates domain focus for a server named after a single certificate service.
For the core domain, `mpt_mg_cnf_consultar` provides the single essential read operation, so a query-only certificate service has no obvious CRUD gap. The platform side is also broadly covered by `marketplace`, but there is no dedicated credit-balance or query-history tool, and some capabilities are bundled rather than first-class.