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 behavioral traits beyond annotations: it initiates a browser login, returns a link, and distinguishes between permanent (config) and session-only (token) usage. Annotations already state idempotency and non-destructiveness, so the description adds useful context without contradiction.
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 somewhat verbose and rambling, mixing instructions and examples in a long sentence. However, it does lead with the purpose and all information is relevant, so it is acceptable but not tight.
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 authentication tool with one optional parameter and no output schema, the description covers the essential workflow and both usage modes. It lacks details about error handling or post-auth state, but is otherwise complete.
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 has zero description coverage and the only parameter (token) is optional. The description fully explains its meaning (a JWT access token) and the two calling conventions: with the token for session login, or without it to get the login link.
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 function: authenticating the user for MCP.AI in IDE agents. It specifies the workflow (browser login, copy token) and distinguishes it from sibling tools (none of which are authentication-related).
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 guidance: recommends adding the token to the server config for permanent access, or using the session-only login by pasting the token. Also explains when to call with no args to get the link vs. with the token.
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 are clearly distinct: restituicao_irpf_consultar is the only domain-specific tool, and the platform utilities (marketplace, report_bug, show_version, toolkit_info) each serve a unique purpose. However, authenticate and connect both relate to connection/auth status, creating slight overlap.
Tool names follow no single convention: some are verbs (connect, authenticate, show_version), some are nouns (marketplace, toolkit_info), and one uses Portuguese snake_case (restituicao_irpf_consultar). The mixed styles are readable but inconsistent.
With 7 tools, the count is reasonable and falls within the ideal range. However, most tools are generic platform utilities that could arguably be separated from the domain-specific IRPF service, but the total is still well-scoped.
The core domain operation—consulting an IRPF refund status—is fully covered by restituicao_irpf_consultar. Minor gaps exist (e.g., no batch query or history retrieval), but the essential use case is complete. The platform tools add ecosystem coverage.