AI agents call pje_consultar_precedentes_bnp 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 queries precedents from the National Precedents Bank (BNP) maintained by the CNJ (Brazilian National Justice Council). It retrieves existing legal information without creating, modifying, deleting, or executing any operations. The action is read-only with no side effects.
From the tool's definition Tool name 'pje_consultar_precedentes_bnp' contains 'consultar' (consult/query). Description states 'Consulta precedentes' (queries precedents) in the BNP database. No modification, deletion, or execution of code/commands is indicated.
Attacks that exploit this kind of access
Consulta precedentes no Banco Nacional de Precedentes (BNP) do CNJ. 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_precedentes_bnp: 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_precedentes_bnp 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_precedentes_bnp 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_precedentes_bnp. 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_precedentes_bnp 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 →