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 provide readOnlyHint=false, idempotentHint=true, and destructiveHint=false, which the description does not contradict. The description adds context about the distinction between permanent (config-based) and session-only authentication, and explains that calling with no args returns a link, enriching the behavioral model beyond the 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 appropriately sized for the complexity, covering multiple auth modes without fluff. It front-loads the core purpose and then details the token and no-arg behaviors. While a bit dense, every sentence contributes necessary information, so it earns a high score.
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 tool with one optional parameter and no output schema, the description is complete. It explains the main purpose, the two authentication methods (permanent config vs. session token), and the no-arg behavior, leaving no critical gaps for an agent to invoke it 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 0% schema description coverage, the description fully compensates by explaining the token parameter's usage: call with { token: "<jwt>" } after paste, and that omitting it yields the link. This gives clear meaning to the otherwise bare schema and clarifies optionality.
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 to MCP.AI for IDE agents, with a clear verb ('authenticate') and resource (MCP.AI server). It differentiates from sibling tools by detailing the login flow and token-based session/permanent authentication methods, making its scope unambiguous.
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 when-to-use guidance: for browser login and token retrieval, with two clear alternatives—permanent via config header or session-only via token parameter. It also instructs when to call with no args to get the link, effectively mapping usage scenarios to invocation patterns.
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 Mercos tools are clearly separated by resource type (clientes, pedidos, produtos, etc.) with consistent list/create/update patterns. The only potential confusion is between the platform-level tools (authenticate, connect, marketplace, toolkit_info) and the Mercos-specific tools, but their descriptions are distinct enough. The marketplace tool is overloaded with many sub-actions (search, describe, invoke, install, subscribe, etc.) which could be ambiguous, but it's a single tool with a clear purpose.
Mercos-specific tools follow a consistent pattern: mercos_<verb>_<resource> (e.g., mercos_list_clientes, mercos_create_pedido, mercos_update_produto). Platform tools use simple verbs (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) which are consistent in style but not following the same verb_noun pattern. The naming is mostly predictable, with minor deviation for platform tools.
25 tools is on the higher end but still reasonable for a server that combines a platform toolkit (marketplace, auth, etc.) with a full ERP integration (Mercos). The Mercos tools cover 8 resources with list/create/update where applicable, which justifies the count. It's slightly heavy but each tool has a clear purpose.
The Mercos integration covers the main CRUD operations for core entities (clientes, pedidos, produtos, tabelas_preco) with list, create, and update. Missing delete operations for most resources, and some resources only have list (categorias, comissoes, condicoes_pagamento, titulos, transportadoras, usuarios) which is fine for reference data. The platform side is comprehensive with marketplace, auth, and toolkit management. Minor gaps like no delete for Mercos entities, but agents can work around.