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 indicate idempotentHint=true and destructiveHint=false, and the description aligns with these. The description adds behavioral context beyond annotations: it explains that the token can be non-expiring if added to config, or session-only if pasted, and that calling with no args returns a link. It does not contradict annotations. It could mention that this is a write operation (setting credentials) but the idempotent hint covers that. The description adds useful context about the two modes of operation.
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 sentence but quite dense, covering multiple scenarios. It is front-loaded with the tool's purpose and then explains usage. It could be slightly more structured (e.g., separating the two modes), but it is efficient and every clause adds value. No wasted words.
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 tool's complexity (two authentication modes, optional parameter, browser interaction), the description covers the key aspects: how to get the link, how to use the token, and the permanent vs session distinction. It lacks details about the return value (e.g., what the link looks like, success/failure responses), but there is no output schema, so the description could be more complete. However, for an authentication tool, the essential information is present.
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?
Schema description coverage is 0%, so the description must compensate. It does explain the 'token' parameter: it should be a JWT pasted by the user, and calling with no args is also valid. This adds meaning beyond the schema, which only defines 'token' as a string. The description clarifies the optional nature and the format (JWT). This is good compensation for the lack of schema descriptions.
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 an IDE agent by logging in via browser and obtaining an access token. It distinguishes itself from siblings by focusing on authentication, while siblings like 'connect' and 'marketplace' serve different functions. The verb 'authenticate' is specific and the resource (access token) is identified.
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: it explains two ways to use the tool (permanent config-based token vs session-only token), when to call with no args to get the link, and when to call with a token. It also mentions the alternative of adding the token to the server's config, which is a clear alternative path. This is excellent guidance for an agent deciding how to 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.
The set mixes one real domain tool with a cluster of platform-management tools—connect, authenticate, toolkit_info, and marketplace—whose boundaries overlap around connection status, accounts, and running MCPs. The marketplace tool especially conflates searching, installing, invoking, and reporting, making it hard for an agent to know which entry point to use.
There is no consistent naming convention: most tools are short English verbs or verb_noun pairs like connect, report_bug, and show_version, while the only domain tool is a long Portuguese underscore-heavier name, detran_ba_debitos_consultar. Mixed languages and inconsistent underscore usage make the tool surface feel fragmented.
Seven is not an extreme number, but six of the seven tools are generic platform infrastructure and only one actually fulfills the DETRAN debt consultation purpose. The count is therefore borderline: not bloated in raw volume, but conceptually top-heavy with meta tools and thin on domain-specific capabilities.
For a read-only DETRAN debt consultation tool, the core operation is covered by detran_ba_debit_consultar, and all base steps around authentication, connection, and marketplace billing are present. The main gaps are practical niceties like explicit wallet/balance visibility and post-query domain actions such as payment or receipt generation, but those may lie outside this server's intended scope.