POST /v1/contact/search. Search for contacts at specified companies. Returns a job_id (async, 202). enrich_fields required (at least one of contact.emails or contact.phones). Use company_list (slug) instead of domains to search a saved list.
AI agents call contact_search to retrieve information from DataMerge MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
contact_search retrieves contact data based on search criteria. Although it triggers an asynchronous enrichment job, the tool itself is a read operation that queries and returns existing contact records. No data is created, modified, deleted, or irreversibly changed. The async job_id mechanism is typical of search APIs that perform background enrichment to enhance results, but the primary function is data retrieval.
From the tool's definition Tool performs a search operation that 'returns a job_id (async, 202)' to retrieve contact records. The operation is explicitly a search/query function with no mention of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
POST /v1/contact/search. Search for contacts at specified companies. Returns a job_id (async, 202). enrich_fields required (at least one of contact.emails or contact.phones). Use company_list (slug) instead of domains to search a saved list. It is categorised as a Read tool in the DataMerge MCP MCP Server, which means it retrieves data without modifying state.
Register the DataMerge MCP server in PolicyLayer and add a rule for contact_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 DataMerge MCP. Nothing to install.
contact_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 contact_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 contact_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.
contact_search is provided by the DataMerge MCP server (poolside-ventures/datamerge-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 →