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 discloses behavioral details beyond annotations: it explains that calling with no args returns a link, passing a token yields session-only login, and config header gives a permanent non-expiring connection. This complements the idempotentHint and readOnlyHint annotations 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 verbose and mixes purpose with step-by-step instructions. It could be streamlined into a clearer structure. Redundant phrasing like 'log in in the browser, copy the access token' adds wordiness.
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?
Given the simple tool (one optional param, no output schema), the description covers both authentication flows (permanent config and session token) and the no-args behavior. It is fully self-contained for an agent to invoke correctly.
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 'token' parameter is fully explained: it should contain a JWT pasted by the user. The description also specifies the no-args behavior, which is not evident from the schema. This adds significant meaning beyond the bare schema definition.
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: authenticating MCP.AI for IDE agents via browser login and token acquisition. It distinguishes from siblings like 'connect' by specifying the IDE-agent context. However, the purpose is somewhat buried within usage instructions.
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?
It provides explicit guidance: call with no args to get the login link, or pass a JWT token for session-only login. It also recommends permanent configuration via Authorization header, covering both use cases. This is sufficient for an agent to decide when to use it.
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 set mixes a single domain-specific tool (acordos_leniencia_consultar) with several generic platform tools (authenticate, connect, marketplace, report_bug, show_version, toolkit_info). While most platform tools have distinct purposes, connect and toolkit_info both report status, and marketplace's broad meta-capabilities overlap with the dedicated tools, creating boundary confusion.
Tool names use inconsistent conventions: Portuguese snake_case (acordos_leniencia_consultar) alongside English single words and compound names (authenticate, report_bug, toolkit_info). There is no uniform verb_noun pattern, and the language switch adds inconsistency.
Seven tools is a reasonable count, but the scope is mismatched: the server name implies a leniency-agreement domain, yet six of seven tools are generic MCP platform utilities. This makes the tool set feel bloated with unrelated functionality or severely underpopulated with domain-specific tools.
The only domain-relevant tool is acordos_leniencia_consultar, a single query operation. There are no other read or write operations for leniency agreements (e.g., listing, filtering, detailed views), making the surface severely incomplete for the stated domain.