AI agents call find_citing_cases to retrieve information from Legal without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and searches legal citation data to answer the question 'who cited this case later?'. It is a read-only query operation analogous to searching a legal database. There are no side effects, no code execution, no data modification, and no destructive actions. The low severity reflects that retrieving publicly available legal information poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'find_citing_cases' and description 'Find cases that cite a specific opinion' indicate a search/query operation that retrieves existing case law data without modifying, executing code, or triggering external operations.
Attacks that exploit this kind of access
Find cases that cite a specific opinion (who cited this case later?). It is categorised as a Read tool in the Legal MCP Server, which means it retrieves data without modifying state.
Register the Legal MCP server in PolicyLayer and add a rule for find_citing_cases: 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 Legal. Nothing to install.
find_citing_cases 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 find_citing_cases 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 find_citing_cases. 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.
find_citing_cases is provided by the Legal MCP server (jscottym/legal-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 →