transfer_to_agent · MCP Search Server MCP: Risk & Policy

WHAT IT DOES

What transfer_to_agent does on MCP Search Server

AI agents invoke transfer_to_agent to trigger actions in MCP Search Server. 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 transfer_to_agent needs a policy

Transferring control to an agent triggers an external operation whose effects depend on the agent's subsequent actions. This is an Execute-category action because it initiates a potentially broad chain of operations (as evidenced by the sibling tools including run, workflows-run, and agent_function).

From the tool's definition Transfer control to the agent

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

transfer_to_agent Rate-limited

transfer_to_agent 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": {
    "transfer_to_agent": {
      "limits": [
        {
          "counter": "transfer_to_agent_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 MCP Search Server, so you can run agents against it safely.

FAQ

Questions about transfer_to_agent

What does the transfer_to_agent tool do? +

Transfer control to the agent. It is categorised as a Execute tool in the MCP Search Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on transfer_to_agent? +

Register the MCP Search Server MCP server in PolicyLayer and add a rule for transfer_to_agent: 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 Search Server. Nothing to install.

What risk level is transfer_to_agent? +

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

Can I rate-limit transfer_to_agent? +

Yes. Add a rate_limit block to the transfer_to_agent 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 transfer_to_agent completely? +

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

transfer_to_agent is provided by the MCP Search Server MCP server (nghiauet/mcp-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.