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?
The description covers behavioral traits beyond annotations: permanent versus session-only login, browser flow, and configuration options. It adds context about token expiration and non-expiring connections. Annotations indicate idempotent and non-destructive, and the description does not contradict these; it enhances understanding.
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 three sentences and front-loaded with the primary action. It includes extra context like 'MCP.AI for IDE agents' and parentheticals, which are useful but slightly verbose. Overall, it is efficient and each sentence contributes.
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 tool with one optional parameter and no output schema, the description covers use cases, persistence, and session behavior. It does not state what the tool returns, but that is a minor omission given the tool's simplicity.
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 input schema lists a single optional string 'token' with no description (0% coverage). The description adds meaning by explaining the token is a JWT copied from the browser, and how to use it (paste for session login, omit to get link). This compensates well for the schema's lack of detail.
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 authenticates the user for IDE agents, using specific actions like 'log in' and 'copy the access token'. It implies the tool's purpose is authentication, but it does not explicitly contrast with sibling 'connect', so it lacks full sibling differentiation.
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 guidelines for two modes: adding a permanent config header versus pasting a session token. It explains when to call with a token and when to call with no args. However, it does not mention when to use this tool over alternatives like 'connect'.
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 have distinct roles, but marketplace is a catch-all that overlaps with toolkit_info (list_tools vs. installed MCPs) and authenticate/connect both deal with connection state. The mix of PIS-specific and platform-level tools also creates ambiguity about which tool handles a given request.
All names use lowercase with underscores, which is consistent, but the naming style varies: some are imperative verbs (authenticate, connect, report_bug), some are nouns (marketplace, toolkit_info), and one is Portuguese verb-noun (pis_consultar). This mixed pattern breaks the expected verb_noun consistency.
Seven tools is a reasonable count, but for a server named 'PIS (Ministério do Trabalho)', only one tool actually relates to PIS. The other six are generic MCP platform utilities (marketplace, auth, version, etc.) that do not belong under this name, making the count inappropriate for the apparent purpose.
The PIS domain is covered by only a single consultation tool; there are no other PIS operations (e.g., statement retrieval, updates). The platform utilities are comprehensive for managing MCPs, but they are irrelevant to the core domain. This leaves the surface feeling incomplete for a server claiming to provide PIS services.