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 are minimal (no readOnly, not destructive), so description carries the burden. It explains the tool's behavior in detail—initiating a login flow, accepting a token, returning a link, and supporting permanent vs session-only auth—adding significant context beyond annotations.
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?
Concise but information-dense, covering purpose, two usage modes, and invocation details in two sentences. Well-structured with no filler; each clause adds value.
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 an authentication tool with no output schema, the description provides sufficient context: what to expect (link or token acceptance), how to use each method, and the overall workflow. It addresses all practical aspects for an IDE agent.
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 has no parameter descriptions (0% coverage), but the description fully explains the 'token' parameter (a JWT) and the behavior of calling without it (returns link). This entirely compensates for the missing schema docs.
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 to MCP.AI for IDE agents. It specifies the exact flow (browser login, copy token) and distinguishes it from siblings like 'connect' by focusing on 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?
Provides explicit usage instructions: two methods (permanent via config header, or session via token parameter), and distinguishes when to use each. Also explains how to call with no args to get the link, leaving no ambiguity about invocation.
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.
Most tools target obvious separate concerns, but marketplace is a mega-tool that bundles actions like report_bug, list_tools, install, and prompt management, while report_bug and toolkit_info also exist separately. This creates real overlap and requires careful reading to pick the right entry point.
All names use lowercase snake_case, which helps, but the semantic pattern is inconsistent: authenticate and connect are bare verbs, report_bug and show_version are verb+noun, marketplace and toolkit_info are noun-like, and sintegra_mt_consultar is a Portuguese object+verb construction. The names are readable but do not suggest one predictable convention.
Seven tools is a reasonable, non-bloated count for an MCP server. However, the marketplace tool contains a large number of sub-operations and effectively acts as many tools in one, while report_bug appears both separately and inside marketplace, so the surface is less clean than the raw count suggests.
The main lifecycle is covered: authentication, connection status, marketplace discovery/invoke/install, toolkit state, versioning, feedback, and the Sintegra-MT query itself. For a read-only data consultation, full CRUD is not expected; missing dedicated wallet-balance/top-up and disconnect/deauth tools are notable but workable via marketplace links.