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 provide safety hints (idempotent, non-destructive), and the description adds valuable context: the browser login step, the distinction between permanent config-based auth vs session-only token paste, and the behavior of calling with no arguments. It doesn't mention error handling or token invalidation, but the added context is meaningful.
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?
Three short sentences/sentence fragments cover context, best-practice config, and runtime usage. No redundant filler; each clause contributes actionable information. The structure effectively front-loads the purpose.
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 simple 1-optional-param tool with no output schema, the description covers the main behaviors: obtaining a link and logging in with a token. It doesn't explicitly state the return value when a token is provided (e.g., success message), but the outcome 'session-only login' is implied. Minor gap given no output schema.
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 full burden. It clearly explains the 'token' parameter as a JWT to paste for session login, and notes that omitting it returns the login link. The optionality and purpose of the parameter are fully clarified.
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 this is the authentication/login tool for MCP.AI IDE agents. It specifies the action ('log in in the browser, copy the access token') and the two invocation modes, distinguishing it from sibling tools like connect or toolkit_info which serve different purposes.
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 guidance on when to call with a token (session-only login) versus with no args (get the link), and recommends a persistent config header as an alternative to the runtime call. It lacks explicit 'don't use this when...' wording, but the two-path guidance is clear.
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.
Several tools deal with authentication and connection state (authenticate, connect, toolkit_info), which creates potential misselection. The marketplace tool also has a broad scope that could be confused with general platform utilities, while the SINTEGRA-specific tool is clearly distinct.
Tool names mix several styles: English imperative verbs (authenticate, connect, report_bug), a bare noun (marketplace), a noun+verb compound (toolkit_info), and a Portuguese verb-final name (sintegra_sc_consultar). No consistent naming convention is followed.
Seven tools is a well-scoped count for a server that combines general MCP platform utilities with a single domain-specific consultation tool. Each tool earns its place without unnecessary bloat.
The SINTEGRA SC domain is a read-only data source, so the single consult tool is adequate. Platform-level features (auth, status, marketplace, version, bug reporting) are also covered, though there is no explicit credit or history management for consultations.