Search for people at companies. Filter by title, seniority, department, or company attributes like sector and technology. Emails are SMTP-verified with confidence scores.
AI agents call find_people to retrieve information from AgentData MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves structured data (people profiles, contact information, seniority levels) from AgentData's platform without creating, modifying, deleting, or executing operations. The SMTP verification is a confidence scoring mechanism for existing data, not a destructive or write operation.
From the tool's definition Tool performs search and retrieval of people data with filtering capabilities. Description states it 'Search[es] for people' and returns 'Emails are SMTP-verified with confidence scores' — pure lookup and query operations with no side effects.
Attacks that exploit this kind of access
Search for people at companies. Filter by title, seniority, department, or company attributes like sector and technology. Emails are SMTP-verified with confidence scores. It is categorised as a Read tool in the AgentData MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AgentData MCP Server MCP server in PolicyLayer and add a rule for find_people: 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 AgentData MCP Server. Nothing to install.
find_people 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_people 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_people. 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_people is provided by the AgentData MCP Server MCP server (nick-timms/agentdata-mcp-server). 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 →