run_contact_search_unenriched · DataMerge MCP: Risk & Policy

WHAT IT DOES

What run_contact_search_unenriched does on DataMerge MCP

AI agents invoke run_contact_search_unenriched 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_unenriched needs a policy

The tool uses an HTTP POST to execute a synchronous search operation on an external API. While the primary effect is retrieval (returning contact records), POST-based operations that trigger server-side processing fall under Execute rather than Read. No data is modified or deleted, so severity is medium — misuse could expose contact data but has limited blast radius.

From the tool's definition POST /v1/contact/search/unenriched/sync — triggers a synchronous operation via HTTP POST that executes a search and returns results inline

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_contact_search_unenriched Rate-limited

run_contact_search_unenriched 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_unenriched": {
      "limits": [
        {
          "counter": "run_contact_search_unenriched_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_unenriched

What does the run_contact_search_unenriched tool do? +

POST /v1/contact/search/unenriched/sync. Synchronous unenriched contact search — returns contacts inline (no polling). Requires the. 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_unenriched? +

Register the DataMerge MCP server in PolicyLayer and add a rule for run_contact_search_unenriched: 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_unenriched? +

run_contact_search_unenriched 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_unenriched? +

Yes. Add a rate_limit block to the run_contact_search_unenriched 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_unenriched completely? +

Set action: deny in the PolicyLayer policy for run_contact_search_unenriched. 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_unenriched? +

run_contact_search_unenriched 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.