session_start · Pokeclaw MCP: Risk & Policy

WHAT IT DOES

What session_start does on Pokeclaw

AI agents invoke session_start to trigger actions in Pokeclaw. 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 session_start needs a policy

This tool executes arbitrary code or commands via spawned agent sessions on the host machine. While the description is incomplete, the core action—spawning and controlling external sessions—clearly fits Execute.

From the tool's definition "Spawn a new coding agent session" — creates and launches external processes (Codex CLI or Claude Code sessions) whose behavior depends on arguments passed by the caller.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

session_start Rate-limited

session_start 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": {
    "session_start": {
      "limits": [
        {
          "counter": "session_start_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 Pokeclaw, so you can run agents against it safely.

FAQ

Questions about session_start

What does the session_start tool do? +

Spawn a new coding agent session. Both agents run the task and exit when done — a status of. It is categorised as a Execute tool in the Pokeclaw MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on session_start? +

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

What risk level is session_start? +

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

Can I rate-limit session_start? +

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

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

session_start is provided by the Pokeclaw MCP server (madebydia/pokeclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.