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?
The description adds context beyond annotations: it explains the difference between permanent (non-expiring) and session-only login, and that calling with no args yields a link. Annotations indicate idempotentHint=true, and the description aligns with that. It also targets IDE agents, which is extra context.
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 two sentences with dense information, but it's somewhat run-on and mixes user instructions with agent instructions. Still, every clause adds useful detail and there is minimal waste.
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?
The tool is simple, but the description covers the main behaviors: permanent vs session, no-args behavior, and token format. No output schema exists, but the description gives enough context for an agent to invoke it correctly.
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 schema only has an optional token string with no description. The description clarifies the token is a JWT and explains concrete usage patterns: call with { token: '<jwt>' } or with no args to get a link. This significantly adds meaning beyond the 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 explains the tool's function: handling authentication by either generating a login link or accepting a JWT token for session login. It distinguishes from sibling tools by focusing on the auth flow for MCP.AI and IDE agents.
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 guidance on two modes: permanent configuration via server header vs session-only token, and recommends the permanent approach as 'Best'. It also tells when to call with no args vs with token, offering clear usage context, though it does not explicitly list exclusions or alternatives.
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 overlap: connect and toolkit_info both report connection status, and marketplace also lists installed tools. authenticate and connect both handle login/credentials, making it difficult to choose the right tool for a given authentication task.
The tool names mix verb-based (authenticate, connect, report_bug), noun-based (marketplace, toolkit_info), and a Portuguese compound (simples_nacional_consultar). There is no consistent naming pattern or language convention across the set.
Seven tools is a reasonable number, but several serve overlapping platform-management purposes (connect, toolkit_info, marketplace) and only one tool relates to the nominal domain of Simples Nacional. The count is acceptable, but the set feels padded with utilities that could be consolidated.
The server's main purpose, consulting Simples Nacional, is covered by a single tool with only one operation (simples_nacional_consultar). There is no broader domain coverage (e.g., batch queries, tax statements, or other company data), and the remaining tools are generic platform utilities that don't fill that gap.