Finds people matching a company
AI agents call find_matches to retrieve information from MCP Traits Matcher without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data (matching people to company job descriptions) with no side effects. It computes similarity metrics and returns results but does not create, modify, delete, or trigger external actions. The operation is read-only and returns informational results for decision-making.
From the tool's definition Tool performs a matching operation to 'find people matching a company' using 'Euclidean distance' calculation.
Attacks that exploit this kind of access
Finds people matching a company. It is categorised as a Read tool in the MCP Traits Matcher MCP Server, which means it retrieves data without modifying state.
Register the MCP Traits Matcher MCP server in PolicyLayer and add a rule for find_matches: 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 Traits Matcher. Nothing to install.
find_matches 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_matches 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_matches. 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_matches is provided by the MCP Traits Matcher MCP server (waifuai/mcp-traits-matcher). 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 →