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 only say idempotent, read-only=false, not destructive. The description adds meaningful behavioral context: the tool can return a login link, accept a JWT for session auth, and suggests a config-based permanent auth path. It doesn't explicitly state whether calling with a token changes server state, but the idempotent annotation covers repeated calls.
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 with several clauses and embedded instructions, making it somewhat dense and hard to parse quickly. While it is information-rich and front-loads the key action, the structure could be cleaner with separate sentences for permanent vs session auth.
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 one optional parameter and no output schema, the description covers the main usage scenarios: getting the login link, pasting a token, and configuring a permanent header. It doesn't describe response shapes, but for an auth tool with this simplicity, the coverage is adequate.
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 the optional `token` parameter is a JWT to be pasted for session-only login, and that omitting it returns the login link. This clearly adds meaning beyond the bare string schema.
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: authenticating an IDE agent via browser login and access token. It distinguishes two modes (config header for permanent connection, inline token for session-only) and provides an alternative call style with no args to get the login link. It is not a textbook verb+resource phrasing but is specific and understandable.
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 walks through when to use each invocation pattern: add the token to config for a permanent, non-expiring connection, or paste it for session-only login. It tells the agent exactly how to call the tool with or without the token, which is strong usage 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 server mixes platform-management tools (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) with one domain-specific tool (mpt_mt_cnf_consultar). The platform tools have overlapping purposes: authenticate and connect both deal with credentials/connection status, while marketplace and toolkit_info both provide current state and capability discovery. An agent could confuse which tool to call for a connection vs. catalog search vs. status query.
Naming is inconsistent: generic English verbs (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) mix with a Portuguese snake_case domain tool (mpt_mt_cnf_consultar). The platform tools are mostly single-word/verb-style, but marketplace is a noun and toolkit_info is hyphenated, lacking a consistent verb_noun pattern.
7 tools is a reasonable count, but most are meta/platform utilities (authentication, marketplace, version, status) surrounding a single business tool. This feels like a platform wrapper with a demo MCP rather than a focused server; the business functionality is underweighted relative to the maintenance tooling.
The only domain action is a simple consultation (mpt_mt_cnf_consultar) that returns a certificate; there is no follow-up tool for history, validation, cancellation, or detailed lookup. The non-domain tools cover platform operations but the core service lacks depth, so an agent can only query and is otherwise at a dead end.