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 mark the tool as idempotent and non-destructive; the description adds meaningful context that the config-based token is permanent/non-expiring while a pasted token is session-only. It also clarifies that calling with no args returns a link, which goes beyond the structured annotations and does not contradict them.
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 two sentences and front-loaded with the tool's purpose. It uses 'Best:' and 'Or' to structure two usage paths cleanly. Minor jargon like 'MCP.AI' and 'Cursor, etc.' adds context without being overly verbose.
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 both call patterns and the permanent/session distinction, but it does not state what the tool returns when called with a token (e.g., success message or validation error). Since there is no output schema and no structured return information, this is a meaningful gap for an agent relying on the description to handle the tool's response.
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 defines an optional 'token' string with 0% coverage, but the description compensates by explaining 'token' is a JWT used for session-only login and that omitting it returns a login link. This gives the agent clear semantics for the only parameter.
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 authenticates to MCP.AI by logging in and obtaining an access token, with concrete steps for browser login and token handling. It names the resource (authentication for MCP.AI) and the verb (log in), but it does not explicitly differentiate from the sibling tool 'connect', which may serve a similar role.
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 explicit usage modes: adding the token to server config for a permanent connection, or calling with a token for a session-only login, and calling with no arguments to get the login link. This provides clear context for when to use each invocation, though it does not state when to prefer this tool over alternatives like 'connect'.
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 server mixes two distinct domains (HiveCloud fiscal documents and mcp.ai platform controls) with several similarly-named tools (hivecloud_list_ctes vs hivecloud_get_cte vs hivecloud_cte_xml; hivecloud_list_mdfes vs hivecloud_get_mdfe). The generic 'authenticate', 'connect', and 'toolkit_info' overlap in connection/account status purposes, creating ambiguity about which to call for setup.
Tools mostly follow a 'hivecloud_<domain>_<action>' pattern (e.g., hivecloud_cte_emitir, hivecloud_cte_cancelar), but there are exceptions like 'hivecloud_avaliar' (short verb without domain), 'get_cte' vs 'list_ctes' (tense/plural inconsistency), and generic tools 'authenticate', 'connect', 'report_bug' that don't follow the pattern. Mixed Portuguese/English verbs further reduce consistency.
With 33 tools, this is on the heavy side. The domain spans CT-e, MDF-e, NF-e, DC-e, plus platform management (marketplace, toolkit, bug reporting, versioning) — it bundles too many concerns into one server. Several tools (report_bug, show_version, marketplace) feel unrelated to HiveCloud fiscal document handling, making the count feel bloated.
For the CT-e and MDF-e lifecycle, the surface is quite complete: create from NF-e, emit, cancel, edit (carta de correção), delete drafts, print DACTE/DAMDFE, export XML, list/get, and even a travel report. DC-e and NF-e are lighter (only list/query), and missing tools like 'create_mdfe' (no draft creation for MDF-e) or 'update_mdfe' (only cancel/end) are notable gaps. However, core workflows are well covered.