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 explains behavioral traits not covered by annotations: it describes two different invocation modes and their effects (returning a link vs establishing a session). It also notes the permanent/non-expiring nature of the header approach. Annotations already indicate non-read-only, non-destructive, and idempotent, and the description aligns with these 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 somewhat dense but each sentence carries relevant information: the target audience, the auth flow, the two modes, and the call variants. It could be tightened slightly but remains efficient and front-loaded with the purpose.
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 there is no output schema, the description should ideally clarify what the tool returns in each mode. It implies the no-arg call returns a link, but does not state what happens when a token is passed (e.g., success message or session object). It also doesn't differentiate from sibling 'connect', but overall it provides sufficient context for an agent to invoke correctly in common scenarios.
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 schema only lists an optional 'token' property with no description. The tool description fully compensates by specifying the token is a JWT, how to pass it, and what happens when no args are provided. This adds meaningful context far beyond the raw schema.
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 IDE agents to MCP.AI. It uses specific verbs ('log in', 'copy the access token', 'paste') and distinguishes two usage modes (permanent header config vs session-only token). This differentiates it from siblings like 'connect' by focusing on MCP.AI-specific token auth.
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 guidance on when to use each approach: permanent connection via config header, session-only via token argument, or call with no args to get the login link. It also mentions the workflow (log in via browser, copy token). However, it doesn't explicitly compare with sibling tools or state when not to use this tool (e.g., for other connection types).
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 tool set is a confusing mix of generic platform operations (marketplace, connect, toolkit_info, report_bug, show_version, authenticate) and one domain-specific tool (car_ambiental_rural_consultar). Several platform tools have overlapping or unclear boundaries: marketplace also lists installed tools, overlapping with toolkit_info; authenticate and connect both deal with authentication status. The single CAR tool stands out as unrelated to the rest, making it hard for an agent to know which tool to pick for a given task.
Tool naming is highly inconsistent: mixed languages (English 'authenticate', Portuguese 'car_ambiental_rural_consultar'), mixed casing (camelCase 'authenticate', 'marketplace' versus snake_case 'car_ambiental_rural_consultar', and multi-word compounds 'show_version', 'toolkit_info', 'report_bug'). There is no discernible verb_noun pattern or consistent style across the set.
While 7 tools is a reasonable count for a typical server, this server is named 'CAR' but only one of the seven tools actually relates to CAR. The other six are generic platform administration tools that would be expected in a completely different server (e.g., an MCP.AI toolkit management server). The count is thus inappropriate for the server's stated domain, as the majority of tools are out of place.
For a server ostensibly about CAR (Cadastro Ambiental Rural), the only domain tool is a single consult operation. There is no coverage for other plausible CAR workflows (e.g., listing properties, updating data, or exporting information). The remaining platform tools are unrelated to CAR, so the domain surface is severely incomplete. Even if the intended scope is solely 'consult,' the presence of many unrelated tools makes the completeness of the set as a whole poor.