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 already indicate readOnly false, idempotent true, destructive false. The description adds context about creating permanent vs. session-only connections and that calling with no args yields a link. It doesn't explicitly state side effects like state mutation, but it implies the auth flow. No contradiction—consistent with annotations.
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 concise (three sentences) and front-loaded with core purpose. Every sentence adds value: process, best practice, alternative. Slightly verbose due to explaining both methods, but no fluff.
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 auth flow complexity (two methods, token parameter, link retrieval) and no output schema, the description covers the essential steps and outcomes. It could specify the exact response when calling with token, but it's sufficiently complete for most use cases.
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 has only 'token' (string) with 0% description coverage. The description fully compensates by explaining that token is the JWT from browser and that it can be omitted to get the link. This adds crucial meaning 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 the user to the MCP server. It uses specific verb 'authenticate' and explains the process (browser login, token), distinguishing it from sibling tools like 'connect' or 'marketplace' by focusing exclusively on 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?
It explicitly provides usage scenarios: best practice (header config for permanent connection) and alternative (session-only via pasted token). It also instructs when to call with token vs. no args to get the link. Clear guidance on when and how to invoke 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.
Most tools have distinct purposes, but 'connect' and 'toolkit_info' overlap in reporting connection status, and 'authenticate' deals with auth similar to 'connect' and 'marketplace' invoke's connect links. 'show_version' is trivial but distinct. The main 'marketplace' tool is a megatool covering many sub-actions, blurring boundaries with 'report_bug' and 'toolkit_info'.
Naming is inconsistent: 'authenticate', 'connect', 'marketplace', 'report_bug', 'show_version' are mostly verb_noun but vary in verb style (some are bare verbs, some noun_verb). 'sintegra_ac_consultar' is Portuguese and does not follow the English pattern, and 'toolkit_info' is noun_verb. Mixed languages and conventions make patterns unpredictable.
7 tools is a reasonable count, but 'marketplace' is an overloaded mega-tool that should arguably be split into multiple tools (search, describe, invoke, install, etc.), making the surface feel heavier than the count suggests. The other tools are sparse, with 'show_version' being near-trivial.
The server mixes platform management, marketplace access, and a single domain-specific query tool (sintegra_ac_consultar). The domain of Brazilian tax information appears incomplete: only one query capability, no history, no credits balance, no CNPJ/CPF variations. Platform side lacks explicit auth revocation or billing details beyond marketplace. Significant gaps for a coherent workflow.