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 side effects like modifying server config, and explains both modes. However, it doesn't detail error handling or token expiration beyond non-expiring mention.
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?
A bit verbose with redundant instructions, but organized into two clear methods.
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?
Explains how to obtain a link and token usage, but lacks explicit description of return value for token call.
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?
Adds meaning to the token parameter by explaining it is a JWT and optional, clarifying its role.
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?
Clearly states it is for authentication, providing instructions to log in and obtain a token. Distinguishes itself from other tools by focusing on login.
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 on when to use permanent config vs session-only, and how to call with or without arguments.
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 separated by entity and action (e.g., projuris_consulta_processo vs projuris_get_processo vs projuris_create_processo). The generic fallbacks (projuris_get, projuris_consulta, projuris_request) are explicitly described as escape hatches for resources without named tools, reducing confusion. A few overlaps exist (e.g., projuris_list_webhook vs a potential consulta_webhook), but descriptions clarify the intended use.
The projuris_* tools follow a consistent pattern: projuris_{verb}_{entity} (e.g., projuris_consulta_processo, projuris_create_pessoa). However, verbs mix languages — English 'create/get/update/list' alongside Portuguese 'consulta' — and one tool uses 'list' while others use 'consulta'. The non-prefixed platform tools (authenticate, connect, marketplace) break the pattern entirely, further hurting consistency.
With 38 tools, this is a heavy surface, but it reflects the breadth of a legal ERP with many entities. Several tools are generic fallbacks that cover the entire API, and the platform-level tools add non-Projuris functionality. The count is borderline: not extremely bloated, but more than necessary for the core CRUD operations.
The named tools cover only a subset of entities (e.g., no create/update for processo or contrato), which would be a gap. However, the generic projuris_request, projuris_get, and projuris_consulta tools provide complete access to all 757 API resources, so no dead ends remain. This hybrid approach makes the surface functionally complete for an agent, though the named tool coverage is uneven.