AI agents call law.judge-lookup to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a lookup/query tool that retrieves publicly available biographical information about federal judges from CourtListener. It has no capability to modify, delete, execute code, or cause financial transactions. The data returned (DOB, DOD, FJC ID, biographical data) is informational only.
From the tool's definition Tool description states it 'Returns parsed judge records with biographical data' and is for 'venue research, judicial profile lookup, and bio enrichment' — all retrieval operations with no modification or side effects.
Attacks that exploit this kind of access
CourtListener federal judge lookup by name. Returns parsed judge records with biographical data (DOB, DOD, FJC ID). Useful for venue research, judicial profile lookup, and bio enrichment. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for law.judge-lookup: 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. Nothing to install.
law.judge-lookup 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 law.judge-lookup 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 law.judge-lookup. 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.
law.judge-lookup is provided by the MCP server (@2sio/mcp). 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 →