execute_code_task · Claude Code Control MCP: Risk & Policy

WHAT IT DOES

What execute_code_task does on Claude Code Control MCP

AI agents invoke execute_code_task to trigger actions in Claude Code Control 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 execute_code_task needs a policy

This tool executes code and shell commands autonomously through an AI agent. Execution of arbitrary code/commands is inherently Execute category. Severity is high because the blast radius depends on system permissions and what the AI decides to run—potential for unintended system modifications, lateral movement, or credential exposure.

From the tool's definition Tool name 'execute_code_task' combined with server description stating 'programmatic execution of coding tasks' and 'run shell commands' and 'agents to search codebases, run shell commands'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_code_task Rate-limited

execute_code_task 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_code_task": {
      "limits": [
        {
          "counter": "execute_code_task_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 Claude Code Control MCP, so you can run agents against it safely.

FAQ

Questions about execute_code_task

What does the execute_code_task tool do? +

Execute a coding task using Claude AI. The AI will autonomously. It is categorised as a Execute tool in the Claude Code Control 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 execute_code_task? +

Register the Claude Code Control MCP server in PolicyLayer and add a rule for execute_code_task: 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 Claude Code Control MCP. Nothing to install.

What risk level is execute_code_task? +

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

Can I rate-limit execute_code_task? +

Yes. Add a rate_limit block to the execute_code_task 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_code_task completely? +

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

execute_code_task is provided by the Claude Code Control MCP server (marc-shade/claude-code-control-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.