recomendar_tools
AI agents call recomendar_tools to retrieve information from Mcp Brasil without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
In the absence of a descriptive definition, the tool name indicates a recommendation engine. Given the server context (querying Brazilian public datasets) and sibling tools that include listing operations (listar_datasets_disponiveis, listar_features), this tool likely reads available tool metadata to provide suggestions. Recommendation without modification is a Read operation.
From the tool's definition Tool name 'recomendar_tools' suggests recommendation functionality; description is empty and uninformative.
Attacks that exploit this kind of access
recomendar_tools. It is categorised as a Read tool in the Mcp Brasil MCP Server, which means it retrieves data without modifying state.
Register the Mcp Brasil MCP server in PolicyLayer and add a rule for recomendar_tools: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Brasil. Nothing to install.
recomendar_tools is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the recomendar_tools rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for recomendar_tools. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
recomendar_tools is provided by the Mcp Brasil MCP server (mcp-brasil/mcp-brasil). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →