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 the behavior of no-args (returns link) and token-pasted (session login), plus the recommendation for permanent header config. Annotations already indicate idempotent non-destructive behavior, and the description adds meaningful detail about the token flow.
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 bit long but every sentence serves a purpose: explaining the flow, the permanent config option, and the two call variants. It's structured logically and not wasteful.
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?
The description covers the essential usage scenarios for an authentication tool with one optional parameter and no output schema. It explains both permanent and session auth, and the no-arg behavior. Could mention what response to expect, but overall complete.
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 has a single optional 'token' parameter with zero description coverage. The description compensates fully by explaining that the token is a JWT for session-only login and that omitting it returns the login link. This adds critical semantic meaning beyond the 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 this is an authentication tool for IDE agents, describing the browser login flow and token usage. The verb 'log in' and references to access tokens establish the purpose. It doesn't explicitly differentiate from sibling 'connect' but is unambiguous.
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?
Provides explicit guidance on two usage modes: permanent config via Authorization header vs session-only by pasting token. It also explains when to call with no args to get the link. This is clear context, though it doesn't discuss alternatives among siblings.
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 marketplace tool is severely overloaded, handling search, describe, invoke, install, subscribe, cancel, and prompt operations all in one. The report_bug capability is duplicated both as its own tool and within marketplace.description, creating ambiguity about which to call.
Mixes multiple conventions: simple verbs (connect), snake_case verbs (authenticate, report_bug, show_version), and a noun_verb pattern (toolkit_info). More confusingly, the one actual domain tool uses Portuguese (sefaz_ba_ipva_consultar) while everything else is in English, and marketplace is a single noun that doesn't convey its enormous scope.
7 tools is a reasonable count and within the well-scoped range. However, marketplace alone describes 10+ sub-operations, so the real surface area is much larger than the count suggests. Borderline but not egregious.
Despite the server name 'SEFAZ BA: IPVA', the domain coverage is minimal — a single consult tool. Missing obvious IPVA operations like payment, debt history, installment plans, or document download. The server spends more effort on platform plumbing (token auth, marketplace, versions) than on the actual IPVA domain.