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 idempotent, non-destructive behavior. The description adds context that token-based login is session-only while config-based is permanent, and that no args returns a link. However, it does not disclose side effects like token validation failures or persistence beyond the session.
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 moderately concise but slightly verbose with informal phrasing and a side note about config setup. It is front-loaded with context, but every sentence is not tightly packed; some words could be trimmed without loss.
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 main invocation patterns but lacks details about response formats, error conditions, or how authentication relates to sibling tools. Since no output schema exists, more explicit return-value information would be beneficial.
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 0% schema coverage for the token parameter, the description thoroughly compensates by explaining it is a JWT from the browser, optional, and that omitting it changes behavior. This adds crucial meaning beyond the bare 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 function: authenticate a user for MCP.AI by providing a login link or accepting a JWT token. It uses specific verbs and resource scope, making it distinct from sibling tools like connect or marketplace.
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 explains two usage modes: passing a token for session-only login, or calling with no args to retrieve a login link. It also recommends the permanent config approach, giving practical guidance on when to use each option, though it does not explicitly contrast with alternative 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 purpose of each tool is not clearly distinct: 'authenticate', 'connect', and 'marketplace' all deal with connection/authentication aspects, and 'authenticate' and 'marketplace' both involve token/credential handling. 'marketplace' also includes a prompt library, blurring boundaries with a hypothetical prompt tool, and 'connect' overlaps with 'toolkit_info' in reporting connection status. This creates high ambiguity for an agent selecting the right tool.
Most tool names are verbs in imperative form (authenticate, connect, show_version, report_bug), but there is a mix: 'marketplace' is a noun, 'toolkit_info' uses a noun+noun structure, and 'sintegra_ro_consultar' breaks the English pattern with Portuguese. While many follow a simple verb, the lack of a consistent verb_noun pattern and the Portuguese exception reduce consistency.
With 7 tools, the count is within the typical recommended range and each tool appears to serve a distinct functional area (auth, connectivity, catalog, feedback, version, a domain-specific query, and toolkit info). However, some tools have overlapping responsibilities, making the count feel slightly bloated; a more consolidated design could reduce it without major loss.
The server appears to focus on a Brazilian tax query (SINTEGRA RO) but only has a single query tool, lacking operations for managing query history, reporting results, or handling errors in a structured way. The platform-level tools are generic but cover market/installation, yet there is no explicit tool for managing credentials beyond 'authenticate' and 'connect', which may leave gaps for full lifecycle management.