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?
Discloses behavior beyond annotations: browser login flow, token handling, permanent vs session-only sessions, and the config header alternative. Consistent with idempotentHint=true and destroys nothing, while adding practical context about how authentication is achieved.
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 sentences, but the second is dense with multiple instructions. Every part adds value, and the main purpose is front-loaded. Slightly long but acceptable.
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?
Covers all invocation variants, parameter meaning, and background context for IDE agents. With one optional parameter and no output schema, the description is largely complete, though it does not explicitly describe the return format.
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?
Though the schema has zero description coverage, the description fully explains the single 'token' parameter: 'call with { token: "<jwt>" } after the user pastes, or with no args to get the link'. This completely compensates for the lack of schema-level documentation.
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: 'log in in the browser, copy the access token' for MCP.AI IDE agents. It uses a specific verb and resource, making it distinguishable from sibling tools like 'connect'.
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 two explicit usage paths: adding the token to server config for a permanent connection, or pasting it via the 'token' parameter for a session-only login. Also explains calling with no args to get the link. Lacks explicit sibling comparison but gives strong contextual 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.
Most tools serve distinct platform functions (auth, status, version, bug reporting) and the sole domain tool is clearly separated. However, connect and toolkit_info both expose connection status, and marketplace is a broad catch-all, creating minor overlap.
Naming is inconsistent: verbs (authenticate, connect, report_bug, show_version), nouns (marketplace, toolkit_info), and a Portuguese object-verb order (receita_pj_consultar) are mixed without a clear pattern. While style is all lowercase with underscores, the convention is not predictable.
At 7 tools the count is within a reasonable range, but six of the seven are platform meta-tools unrelated to the Receita Federal domain suggested by the server name. This dilutes the tool set's purpose and makes it feel cluttered.
The core CNPJ consultation is covered with optional shareholder data, which is appropriate for a public-data lookup. There are no obvious lifecycle gaps since the operation is read-only, though search or batch capabilities are missing directly but could be discovered via the marketplace tool.