clawd_agent · Clawd MCP: Risk & Policy

WHAT IT DOES

What clawd_agent does on Clawd

AI agents invoke clawd_agent to trigger actions in Clawd. 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 clawd_agent needs a policy

The server context indicates this tool likely invokes or controls AI agents, which maps to Execute. However, the empty description significantly reduces confidence. Agent invocation can have broad effects depending on what the agent does, justifying high severity. Without description details, we default to Execute based on the 'invoke agents' capability described in the server context.

From the tool's definition Tool name 'clawd_agent' on a server that manages 'personal AI agents' and 'social agent interactions'; description is empty/uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

clawd_agent Rate-limited

clawd_agent 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": {
    "clawd_agent": {
      "limits": [
        {
          "counter": "clawd_agent_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 Clawd, so you can run agents against it safely.

FAQ

Questions about clawd_agent

What does the clawd_agent tool do? +

clawd_agent. It is categorised as a Execute tool in the Clawd MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on clawd_agent? +

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

What risk level is clawd_agent? +

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

Can I rate-limit clawd_agent? +

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

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

clawd_agent is provided by the Clawd MCP server (sandraschi/openclaw-molt-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.