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?
Beyond annotations (idempotent, non-destructive), the description explains what happens: it provides a login link, accepts a JWT token for session, and distinguishes permanent vs session-based connections. It doesn't disclose side effects like invalidating previous credentials, but the behavior is well outlined.
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 a single paragraph but logically organized with a clear flow: purpose, best method, alternative method, and invocation forms. It's a bit verbose with phrases like 'MCP.AI for IDE agents' but every sentence provides useful guidance, avoiding redundancy.
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 tool with no output schema and moderate complexity (two auth flows), the description covers the key aspects: how to initiate browser login, how to pass a token, and what no-args returns. It doesn't specify the response structure or error conditions, but it's sufficiently complete for an auth tool.
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 'token' string with 0% description coverage. The description compensates by explaining the token is a JWT for session login and clarifies that calling with no args returns the link. This adds meaning beyond the raw schema, though it could detail token format or required auth scopes.
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 this is for authentication: 'log in in the browser, copy the access token' and explains the two login modes. It distinguishes from sibling tools by focusing on IDE agent usage and token-based auth, which is a unique purpose among the siblings.
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 when-to-use guidance: recommends adding token to server config for permanent connection, or pasting token for session-only login, or calling with no args to get a link. It doesn't explicitly compare to the sibling 'connect' tool, but the usage context is clear 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.
The tools serve mostly distinct purposes, but the marketplace tool is a broad catch-all that overlaps with the domain tool (can search for CPF-related MCPs) and includes many sub-actions. Additionally, connect and toolkit_info both report connection status, creating some ambiguity. Detailed descriptions help, but selection risk remains.
Tool names are all lowercase snake_case, but the pattern is inconsistent: some are single verbs (authenticate, connect), some are nouns (marketplace), and only a few follow a verb_noun style. The domain-specific tool uses a different convention (tj_certidao_consultar). This mixed naming makes it hard to predict tool behavior from names alone.
The 7-tool count is within a reasonable range, but the server is named for a specific domain (TJ certificates) yet devotes 6 of 7 tools to generic platform management. This creates a scope mismatch where the domain surface is a single tool and the platform tools feel out of place, though the number itself is not excessive.
The only domain tool covers the core consult operation, but there are no other certidão-related tools (e.g., list past requests, check status, or generate a specific variant). The platform tools do not address the domain's completeness, leaving significant gaps for typical certificate workflows.