run_contact_search · DataMerge MCP: Risk & Policy

WHAT IT DOES

What run_contact_search does on DataMerge MCP

AI agents invoke run_contact_search to trigger actions in DataMerge MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why run_contact_search needs a policy

The tool executes an external enrichment job rather than passively retrieving cached data. It initiates server-side operations that run asynchronously, which classifies it as Execute. The severity is high because uncontrolled contact searches could expose personal/corporate data, invoke expensive API calls, or harvest unauthorized contact information at scale.

From the tool's definition Tool description states 'Agent-friendly contact search' that 'starts the job and polls internally' — this indicates the tool triggers an external operation (starting and polling an enrichment job) whose effects depend on the arguments (domains and…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_contact_search Rate-limited

run_contact_search stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_contact_search": {
      "limits": [
        {
          "counter": "run_contact_search_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches DataMerge MCP, so you can run agents against it safely.

FAQ

Questions about run_contact_search

What does the run_contact_search tool do? +

Agent-friendly contact search. On the first call provide domains and enrich_fields; the server starts the job and polls internally for up to ~${RUN_JOB_DEFAULT_MAX_WAIT_SECONDS}s. If still running, returns {status:. It is categorised as a Execute tool in the DataMerge MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_contact_search? +

Register the DataMerge MCP server in PolicyLayer and add a rule for run_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.

What risk level is run_contact_search? +

run_contact_search is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_contact_search? +

Yes. Add a rate_limit block to the run_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.

How do I block run_contact_search completely? +

Set action: deny in the PolicyLayer policy for run_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.

What MCP server provides run_contact_search? +

run_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.