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 and non-destructive behavior. The description adds context about the two modes (permanent config vs session-only) and the behavior of calling with no args (returns a link). It does not disclose error handling or side effects like invalidating prior tokens, but the added context is valuable within the annotation baseline.
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 a bit dense and runs on, but it is front-loaded with the purpose and every clause adds needed information. It is efficient for the amount of guidance provided, though it could be split into clearer sentences.
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 absence of an output schema, the description covers the core invocation patterns and expected outcomes for the no-args case (returns link). It does not explicitly state what the response is when a token is provided, nor error cases, but the tool is simple enough that this is not a critical gap.
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 'token' without description (0% coverage). The description fully compensates by explaining that the token is a JWT, that it can be omitted to get a login link, and that providing it performs a session login. This is precisely the semantics an agent needs.
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 explicitly states the tool's purpose: to authenticate for MCP.AI in IDE agents by logging in via browser and copying an access token. It clearly distinguishes this from sibling tools by focusing on the authentication/login flow, not just repeating the name.
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 usage scenarios: best practice is adding the token to server configuration for a permanent connection, or pasting it for a session-only login, or calling with no args to get the link. This gives clear when-to-use and how-to-invoke guidance, effectively differentiating between options.
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 clearly distinct purposes: authenticate, connect, marketplace, report_bug, scr_bacen_consultar, show_version, and toolkit_info are each identifiable. However, the marketplace tool bundles many sub-actions (including report_bug, install, list_tools) that overlap with dedicated tools like report_bug and toolkit_info, creating potential confusion.
Naming conventions are mixed: English imperatives (authenticate, connect, report_bug, show_version), noun-based names (marketplace, toolkit_info), and a Portuguese verb phrase (scr_bacen_consultar). This lacks a consistent verb_noun or uniform pattern, making the set feel cobbled together.
With 7 tools, the count is within a reasonable range for a server, but several tools (show_version, toolkit_info, connect) are platform-level utilities rather than domain-specific, slightly diluting the focus on SCR consultation. Still, each tool appears to serve a purpose, so the count is acceptable.
The server's stated domain is SCR (Banco Central credit information), yet only one tool (scr_bacen_consultar) addresses that domain, offering a single query operation. There are no additional tools for historical data, batch processing, or output formatting. While the marketplace can compensate by invoking other MCPs, the core domain surface is severely minimal.