planejar_consulta
AI agents call planejar_consulta 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.
The tool appears to plan or prepare queries against Brazilian public APIs and datasets. The name suggests preparation or planning of queries rather than execution, modification, or deletion. However, confidence is moderate (0.6) because the description is empty, making definitive classification difficult. If it merely prepares queries without executing them, it is a Read operation with low risk.
From the tool's definition Tool name 'planejar_consulta' (plan query) and context of an MCP server that 'enables users to query and cross-reference extensive government datasets' suggests a query planning/preparation function.
Attacks that exploit this kind of access
planejar_consulta. 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 planejar_consulta: 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.
planejar_consulta 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 planejar_consulta 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 planejar_consulta. 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.
planejar_consulta 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 →