AI agents call search_matters 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.
The tool appears to search or list legal matters without modifying data. 'Search' typically retrieves information; the server's practice management via Clio context suggests it queries existing matters rather than creating or deleting them. The empty description prevents us from confirming execution or write capabilities, but the low confidence adjustment accounts for this.
From the tool's definition Tool name 'search_matters' combined with context showing sibling tools like 'get_matter_details', 'get_matter_documents', and 'get_case_details' indicate this is a query/search function for retrieving matter records.
Attacks that exploit this kind of access
search_matters. 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 search_matters: 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.
search_matters 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_matters 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_matters. 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_matters 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 →