AI agents call law.case-verify 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 read-only verification check by comparing citations against an existing corpus. It retrieves information to validate claims but does not modify data, execute arbitrary operations, or produce irreversible side effects. The low severity reflects that misuse would primarily surface incorrect information rather than cause system harm or data loss.
From the tool's definition Tool description states 'Verify every US legal citation inside a passage of text against the real CourtListener corpus' — this is a query/lookup operation against an external database with no modification, creation, deletion, or execution of code.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Verify every US legal citation inside a passage of text against the real CourtListener corpus. Anti-hallucination check before quoting case law. 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-verify: 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-verify 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-verify 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-verify. 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-verify 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 →