claude_prompt_structured · Claudecode MCP: Risk & Policy

WHAT IT DOES

What claude_prompt_structured does on Claudecode

AI agents invoke claude_prompt_structured to trigger actions in Claudecode. 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 claude_prompt_structured needs a policy

This is an Execute category tool because it triggers external code execution (Claude Code CLI) whose behavioral outcomes are determined by user-supplied prompt arguments. Although it runs in a stateless manner, it still executes commands that can have side effects on the local system or external services.

From the tool's definition The tool 'run[s] a one-shot prompt against the Claude Code CLI in headless, stateless' mode. The server description states it 'wraps the headless Claude Code CLI as MCP tools' and 'enables users to execute Claude Code commands.' While the tool name references…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

claude_prompt_structured Rate-limited

claude_prompt_structured 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": {
    "claude_prompt_structured": {
      "limits": [
        {
          "counter": "claude_prompt_structured_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 Claudecode, so you can run agents against it safely.

FAQ

Questions about claude_prompt_structured

What does the claude_prompt_structured tool do? +

Run a one-shot prompt against the Claude Code CLI in headless, stateless. It is categorised as a Execute tool in the Claudecode MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on claude_prompt_structured? +

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

What risk level is claude_prompt_structured? +

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

Can I rate-limit claude_prompt_structured? +

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

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

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