execute_child_tool · MCP Gateway (Parent MCP Server) MCP

WHAT IT DOES

What execute_child_tool does on MCP Gateway (Parent MCP Server)

AI agents invoke execute_child_tool to trigger actions in MCP Gateway (Parent MCP 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 execute_child_tool needs a policy

This tool executes arbitrary operations on child servers without restriction visible in the name. It can trigger Read, Write, Destructive, or Execute actions depending on which child tool is invoked and with what arguments. The highest-severity outcome is Execute (not Destructive or Financial in all cases, but Execute as the baseline action pattern).

From the tool's definition Tool name 'execute_child_tool' indicates execution of arbitrary tools across multiple child MCP servers (filesystem, sqlite, etc.).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_child_tool Rate-limited

execute_child_tool 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": {
    "execute_child_tool": {
      "limits": [
        {
          "counter": "execute_child_tool_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 Gateway (Parent MCP Server), so you can run agents against it safely.

FAQ

Questions about execute_child_tool

What does the execute_child_tool tool do? +

execute_child_tool. It is categorised as a Execute tool in the MCP Gateway (Parent MCP 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 execute_child_tool? +

Register the MCP Gateway (Parent MCP Server) MCP server in PolicyLayer and add a rule for execute_child_tool: 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 Gateway (Parent MCP Server). Nothing to install.

What risk level is execute_child_tool? +

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

Can I rate-limit execute_child_tool? +

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

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

execute_child_tool is provided by the MCP Gateway (Parent MCP Server) MCP server (tomcat2357/mcpgateway). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

execute_child_tool is one line of MCP Gateway (Parent MCP Server)'s registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →