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 include idempotentHint=true and readOnlyHint=false. The description adds context beyond this: it explains the token is a JWT, the session vs permanent distinction, and the behavior when called with no args. This clarifies the tool's side effects and state implications without contradicting the 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?
Two dense sentences deliver all essential information: the purpose, the preferred config method, the session alternative, and the no-args case. There is no fluff; every clause adds value and the description is front-loaded with 'MCP.AI for IDE agents'.
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 tool with one optional parameter and no output schema, the description covers the main usage scenarios (config, token, no-args). It doesn't discuss response formats or error handling, but that's not critical here; the tool's behavior is clearly outlined, making it usable in most contexts.
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 one optional param (token) with no description (0% coverage). The description compensates by explaining that token is a JWT, how to use it (paste for session), and the no-args behavior. This gives the agent enough understanding to use the parameter correctly.
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 an IDE agent with MCP.AI. It specifies the resource (MCP.AI) and the action (login, retrieve token), and distinguishes from siblings by focusing on authentication flows. The verb 'authenticate' is reinforced with detailed steps.
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 provides clear usage context: it explains the recommended permanent approach (config header) versus session-based login (token argument), and notes that calling with no args returns a link. It does not explicitly compare with sibling tools, but the guidance within the tool is solid and actionable.
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.
There is a separate report_bug tool while marketplace also mentions report_bug internally, causing duplication. Additionally, authenticate and connect both deal with authentication/connection status, creating boundary confusion.
Tool names mix English and Portuguese (authenticate vs nfe_completa_consultar), and mix verb forms (authenticate, connect) with noun forms (marketplace, toolkit_info), with no consistent verb_noun pattern.
Seven tools is a reasonable number for a server, but the massive marketplace tool bundles dozens of operations into a single tool, making the set feel both overcrowded and under-represented.
The NFe consultation itself is a single query tool, and the rest are platform utilities not directly related to NFe, so the domain coverage is thin. Missing functions like listing past consultations or managing account credits, though the core consult works.