Find relevant cases using LLM-generated search keywords. The LLM should extract legal keywords from the problem description and provide them for precise case law search.
AI agents call search_cases_by_problem to retrieve information from CourtListener Legal Research MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information from the CourtListener database (case law) in response to search queries. There are no side effects, no data modification, no code execution, and no irreversible actions. It is purely informational retrieval, equivalent to a database query or search operation.
From the tool's definition Tool description states it 'Find[s] relevant cases' using search keywords for 'case law search'. The name includes 'search' and the function is to retrieve and query case information without modification or deletion.
Attacks that exploit this kind of access
Find relevant cases using LLM-generated search keywords. The LLM should extract legal keywords from the problem description and provide them for precise case law search. It is categorised as a Read tool in the CourtListener Legal Research MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CourtListener Legal Research MCP Server MCP server in PolicyLayer and add a rule for search_cases_by_problem: 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 CourtListener Legal Research MCP Server. Nothing to install.
search_cases_by_problem 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 search_cases_by_problem 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 search_cases_by_problem. 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.
search_cases_by_problem is provided by the CourtListener Legal Research MCP Server MCP server (khizar-anjum/courtlistener-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 →