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 useful behavioral context: no args yields a login link, token-based auth is session-only, and config-header auth is permanent. No contradiction 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 compact and front-loaded with purpose, then organized around the two authentication paths using 'Best' and 'Or'. It is slightly dense with setup instructions, but every sentence contributes useful guidance.
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?
For a simple one-optional-parameter tool with no output schema, the description covers invocation modes, session persistence, and the no-arg link flow. It omits response/error details, but those are largely unnecessary given the annotations and simple schema.
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 burden. It defines the `token` parameter as a pasted JWT for session-only login and explicitly documents the optional no-arg usage. Some format constraints could be added, but the core semantics are clear.
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 MCP.AI access for IDE agents, with browser login and a pasted access token. It distinguishes the no-argument flow from the token flow, though it does not explicitly contrast itself with sibling tool `connect`.
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 invocation guidance: call with no args to get a login link, or pass `{ token: "<jwt>" }` after the user pastes a token. It also notes the permanent config-header alternative, but does not discuss when to prefer alternative sibling 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.
The six dfe_* tools are clearly distinguished by key/NSU/sync/quota/account/DANFE, but the platform layer has overlap: connect and toolkit_info both report connection/status, and marketplace contains a report_bug action that duplicates the standalone report_bug tool. The detailed descriptions help, but an agent can still misselect between these near-duplicate entry points.
The dfe_ prefix gives the fiscal tools a recognizable family, but the set mixes Portuguese and English (dfe_consultar_chave vs dfe_list_accounts) and mixes prefixed domain verbs with bare English platform verbs (authenticate, connect, show_version). It is readable and mostly snake_case, but not one consistent convention.
Twelve tools is a reasonable, manageable count. The slight over-inclusion comes from six generic platform/meta tools (marketplace, authenticate, toolkit_info, report_bug, etc.) that sit alongside the DF-e domain tools, making the surface broader than the server name implies.
The receipt-side DF-e workflow is mostly covered: sync, lookup by chave/NSU, quota check, account listing, and DANFE generation all exist. However, there is no manifestation/event tool (ciência, confirmação, desconhecimento), so resumo documents cannot be upgraded to complete XML/DANFE within this server, and the sync description references an auditor_fiscal_auditar_nota tool that is not present.