relay_exec_script · RelayPlane MCP: Risk & Policy

WHAT IT DOES

What relay_exec_script does on RelayPlane

AI agents invoke relay_exec_script to trigger actions in RelayPlane. 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 relay_exec_script needs a policy

This tool executes code with side effects that depend entirely on the script content provided by the agent. While sandboxed (mitigating blast radius somewhat), it can trigger multi-step LLM operations, interact with multiple AI providers, and produce unpredictable outcomes based on workflow logic. The 30s timeout provides some guardrail but does not prevent resource exhaustion or unintended chaining of operations.

From the tool's definition Tool description states 'Execute RelayPlane SDK scripts in a sandboxed environment' and 'write your workflow code'. The name 'relay_exec_script' and explicit execution capability indicate this runs arbitrary code.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

relay_exec_script Rate-limited

relay_exec_script 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": {
    "relay_exec_script": {
      "limits": [
        {
          "counter": "relay_exec_script_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 RelayPlane, so you can run agents against it safely.

FAQ

Questions about relay_exec_script

What does the relay_exec_script tool do? +

Execute RelayPlane SDK scripts in a sandboxed environment. Useful for testing generated workflow code. The SDK is automatically imported - just write your workflow code. Scripts have a default 30s timeout. It is categorised as a Execute tool in the RelayPlane MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on relay_exec_script? +

Register the RelayPlane MCP server in PolicyLayer and add a rule for relay_exec_script: 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 RelayPlane. Nothing to install.

What risk level is relay_exec_script? +

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

Can I rate-limit relay_exec_script? +

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

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

relay_exec_script is provided by the RelayPlane MCP server (relayplane/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.