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 context beyond annotations by explaining the two operation modes (permanent vs session-only) and the link retrieval behavior. It does not contradict the idempotentHint=true annotation, and while it doesn't discuss failure scenarios or token validity, the annotations already declare it non-destructive and safe.
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, front-loaded with the tool's core purpose, and efficiently covers all necessary usage details in a few sentences. No redundant information; every sentence serves a purpose.
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 tool is simple (one optional param, no output schema), and the description provides complete guidance for both invocation patterns, including the trade-off between permanent and session login. It covers everything an agent would need to select and use the tool correctly.
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?
With schema description coverage at 0% and only one optional parameter 'token', the description fully compensates by specifying that 'token' is a JWT and explaining when to provide it (after user pastes) versus when to omit it (to get the link). This adds meaningful 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 the tool's purpose: authentication for MCP.AI IDE agents via browser login and token usage. It specifies the action (log in, copy token) and resource (access token), and distinguishes it from sibling tools by focusing on the authentication flow.
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 provides explicit usage guidance: for permanent connections it recommends configuring the token as a header, while for session-only it instructs to call with a token or with no arguments to get a link. It clearly explains when to use each method and the input for each scenario.
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 serves a distinct purpose: authentication, connection status, marketplace search, bug reporting, SEFAZ consultation, version display, and toolkit state. There is no overlapping functionality; even the two info tools (show_version and toolkit_info) have clear differences.
Tool names are inconsistent in style: some are verbs (authenticate, connect, report_bug), some are nouns (marketplace, toolkit_info), and one uses a compound with underscore (sefaz_consultar). The pattern is not uniform, making it harder to predict tool names from their function.
With 7 tools, the server provides a reasonable set for its purposes, including both domain-specific (sefaz_consultar) and generic management tools. This count falls within the typical range and is not excessive.
The tool set covers authentication, connection management, marketplace, bug reporting, version info, and the core SEFAZ consultation. However, it lacks additional SEFAZ-related operations such as listing or updating documents, which might be expected from a SEFAZ server, but the core consultation is covered.