stateful_chat · AgentSpawn MCP: Risk & Policy

WHAT IT DOES

What stateful_chat does on AgentSpawnMCP

AI agents invoke stateful_chat to trigger actions in AgentSpawnMCP. 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 stateful_chat needs a policy

This tool triggers external LLM API calls and maintains conversation state, making it an Execute-category action — it runs external operations (LLM inference) whose effects depend on arguments. The stateful nature (tracking response_id) means it can persist and chain interactions, but it does not appear to directly delete data or move money, so Execute is the most severe applicable category.

From the tool's definition 'Stateful chat via response_id for continued conversations' on a server described as 'spawning agents with any OpenAI-compatible LLM' and integrating with 'Claude Code, OpenCode, and Codex CLI'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stateful_chat Rate-limited

stateful_chat 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": {
    "stateful_chat": {
      "limits": [
        {
          "counter": "stateful_chat_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 AgentSpawnMCP, so you can run agents against it safely.

FAQ

Questions about stateful_chat

What does the stateful_chat tool do? +

Stateful chat via response_id for continued conversations. It is categorised as a Execute tool in the AgentSpawnMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on stateful_chat? +

Register the AgentSpawn MCP server in PolicyLayer and add a rule for stateful_chat: 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 AgentSpawnMCP. Nothing to install.

What risk level is stateful_chat? +

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

Can I rate-limit stateful_chat? +

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

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

stateful_chat is provided by the AgentSpawn MCP server (sandsaber/agentspawnmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.