AI agents call pje_consultar_processo to retrieve information from Pje without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves judicial process information by process number through the Brazilian PJE system. It performs a read-only query operation with no side effects, data modification, code execution, deletion, or financial implications. The action is purely informational retrieval from a legal database.
From the tool's definition Tool name is 'pje_consultar_processo' and description states it 'Consulta um processo' (consults/queries a process) by number using MNI. The verb 'consulta' (consult/query) indicates retrieval without modification.
Attacks that exploit this kind of access
Consulta um processo pelo número usando o MNI (Modelo Nacional de Interoperabilidade). It is categorised as a Read tool in the Pje MCP Server, which means it retrieves data without modifying state.
Register the Pje MCP server in PolicyLayer and add a rule for pje_consultar_processo: 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 Pje. Nothing to install.
pje_consultar_processo 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 pje_consultar_processo 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 pje_consultar_processo. 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.
pje_consultar_processo is provided by the Pje MCP server (ma-serra/pje-mcp-server2). 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 →