AI agents call law.case-search 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.
The tool performs a search query against public legal records (CourtListener / Free Law Project), which is a read-only operation. It retrieves existing case law information with no side effects, data modification, code execution, or financial implications. The low severity reflects minimal risk even if an AI misuses a legal search query.
From the tool's definition Tool name is 'law.case-search' and description states 'Search US federal + state case law' — this is a retrieval operation that queries a legal database without modifying, executing, or deleting any data.
Attacks that exploit this kind of access
Search US federal + state case law (CourtListener / Free Law Project). 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.case-search: 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.case-search 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.case-search 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.case-search. 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.case-search 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 →