chat_with_agent · Smallest MCP: Risk & Policy

WHAT IT DOES

What chat_with_agent does on Smallest

AI agents invoke chat_with_agent to trigger actions in Smallest. 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 chat_with_agent needs a policy

This tool actively triggers a real-time WebSocket connection and sends messages to a published AI agent, causing external operations to occur. It's not a passive read — it initiates a live interaction session with an external service, making Execute the most appropriate category.

From the tool's definition Hold a TEXT conversation with a published agent over the realtime chat WebSocket (mode=chat)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

chat_with_agent Rate-limited

chat_with_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": {
    "chat_with_agent": {
      "limits": [
        {
          "counter": "chat_with_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 Smallest, so you can run agents against it safely.

FAQ

Questions about chat_with_agent

What does the chat_with_agent tool do? +

Hold a TEXT conversation with a published agent over the realtime chat WebSocket (mode=chat) —. It is categorised as a Execute tool in the Smallest MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on chat_with_agent? +

Register the Smallest MCP server in PolicyLayer and add a rule for chat_with_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 Smallest. Nothing to install.

What risk level is chat_with_agent? +

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

Can I rate-limit chat_with_agent? +

Yes. Add a rate_limit block to the chat_with_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 chat_with_agent completely? +

Set action: deny in the PolicyLayer policy for chat_with_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 chat_with_agent? +

chat_with_agent is provided by the Smallest MCP server (@developer-smallestai/smallest-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.