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 adds behavioral context beyond the annotations by explaining the permanent vs. session-only distinction, the non-expiring nature of the config header approach, and the no-args behavior of returning a login link. It does not describe error cases or what happens on invalid tokens, but it meaningfully supplements the annotation hints.
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 compact and front-loaded with the tool's purpose, then efficiently explains both usage modes. It is slightly run-on with multiple clauses in one sentence, but every part adds necessary information and there is no filler.
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 simple input schema and lack of output schema, the description covers the essential context: browser login, token handling, permanent vs. session auth, and the no-args behavior. It does not describe the response format or post-auth state, but for this tool's complexity the coverage is strong.
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 carries the full burden for parameter meaning. It explicitly explains that the 'token' parameter is a JWT to be pasted for session-only login, and that omitting the parameter returns the login link. This fully compensates for the sparse 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 an IDE agent by logging in via browser and obtaining an access token. It specifies the exact resource (MCP.AI server auth) and the action (log in / authenticate), and the browser-based flow distinguishes it from the sibling 'connect' tool.
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 gives clear usage context with two explicit modes: permanent config-based auth via Authorization header, and session-only login by passing a token. It also explains when to call with no args ('to get the link') versus with a token. However, it does not explicitly mention when not to use this tool or name alternative tools.
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.
Each tool has a distinct core purpose: auth, connection status, the ECAC query, the marketplace, bug reporting, version info, and toolkit state. However, there's some overlap between `connect` and `toolkit_info` (both surface connection state), and `marketplace` is a multifunction blob that also covers billing, prompts, and other capabilities an agent might expect as separate tools.
Most tools follow a clean lowercase verb_noun pattern (authenticate, connect, report_bug, show_version, toolkit_info), but `ecac_perdcomp_consultar` breaks the pattern entirely—it's snake_case but in Portuguese and uses a different verb ordering. This naming mixes languages, making the set feel inconsistent even though the convention itself (utterances separated by underscores) holds.
With 7 tools, the server falls comfortably in the ideal 3-15 range. The count feels right for a platform bootstrapping an ECAC integration: one domain-specific tool plus six infrastructure/meta tools. No tool feels redundant enough to cut, though the market place tool could arguably be split.
For a read-only tax query service, the single `ecac_perdcomp_consultar` tool covers the core use case. However, there's no history, balance/credit check, or query status tool exposed at the top level, and the marketplace's generic dispatch is too broad to guarantee discovery of what the platform can really do.