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 readOnlyHint=false, destructiveHint=false, and idempotentHint=true. The description adds behavioral detail beyond annotations: it explains the two authentication modes (permanent config vs session token), the token format (JWT), and the action of getting a link if no args are provided. This enriches the agent's understanding without contradicting any 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?
The description is a single dense sentence but highly informative. It front-loads the purpose and then details usage modes. No fluff or redundancy. The length is justified given the complexity of the authentication flow, but it could be slightly more structured (e.g., separated sentences) for readability without losing meaning.
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 has no output schema, one optional parameter, and no nested objects. The description covers the key aspects: how to authenticate permanently or temporarily, what to pass, and the behavior when called with no args. It provides complete information for an agent to decide and invoke correctly, and the lack of output details is acceptable since the primary outcome is auth state or a link.
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 single parameter 'token' is a string with zero schema description coverage, so the description must compensate. It does so effectively by explaining that when a token is provided, it's a session-only login, and if omitted, the tool returns a login link. This adds critical context that the schema alone lacks.
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 with MCP.AI for IDE agents by logging in via browser and copying a token. It distinguishes itself from siblings like 'connect' and 'marketplace' by explicitly focusing on authentication. The verb 'log in' and resource 'MCP.AI' plus token handling make the purpose unambiguous.
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 explicit usage guidance: recommends adding the token to the server config for a permanent connection, or using a session-only login by calling with a token or no args to get a link. It clearly explains when each mode is appropriate and gives calling instructions, which is more than sufficient for an agent to select and invoke the tool.
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 distinct, but authenticate and connect overlap in handling credentials and connection URLs, and marketplace can also return connect links. The remaining tools (report_bug, show_version, toolkit_info, tribunal_tjrj_processo_consultar) are clearly separate.
Names follow no consistent pattern: single verbs (authenticate, connect), nouns (marketplace, toolkit_info), verb_noun combinations (report_bug, show_version), and a long Portuguese composite (tribunal_tjrj_processo_consultar). The mix of styles and languages is confusing.
Seven tools is a reasonable size, but six of them are generic MCP platform utilities while the server is titled for a specific process consultation domain. The composition feels mismatched, though not overly large or thin.
For the declared domain (TJRJ process consultation), only a single consult tool exists, which may be sufficient for basic queries. However, there are no related operations (e.g., listing, history), and the platform tools dominate, leaving the domain surface minimal.