send_prompt · OpenClaude MCP Server MCP: Risk & Policy

WHAT IT DOES

What send_prompt does on OpenClaude MCP Server

AI agents invoke send_prompt to trigger actions in OpenClaude 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 send_prompt needs a policy

Sending a prompt to a running LLM session triggers an external computation/operation whose effects depend on the prompt content. This is an Execute-class action: it causes a live session to process arbitrary input, potentially producing outputs that drive downstream actions (especially given this server's described capabilities like hybrid cloud planning and fleet monitoring).

From the tool's definition "Send a prompt to a running OpenClaude session" — triggers execution of an LLM inference session with user-supplied input

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_prompt Rate-limited

send_prompt 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": {
    "send_prompt": {
      "limits": [
        {
          "counter": "send_prompt_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 OpenClaude MCP Server, so you can run agents against it safely.

FAQ

Questions about send_prompt

What does the send_prompt tool do? +

Send a prompt to a running OpenClaude session. It is categorised as a Execute tool in the OpenClaude 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 send_prompt? +

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

What risk level is send_prompt? +

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

Can I rate-limit send_prompt? +

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

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

send_prompt is provided by the OpenClaude MCP Server MCP server (sandraschi/openclaude-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.