ai_chat · Onion MCP: Risk & Policy

WHAT IT DOES

What ai_chat does on Onion

AI agents invoke ai_chat to trigger actions in Onion. 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 ai_chat needs a policy

This tool triggers external AI model inference with arbitrary user-supplied input and conversation history. It executes an external operation whose effects depend on arguments. While it primarily retrieves generated text (Read-like), it runs an external AI service call with stateful context, placing it in Execute.

From the tool's definition 与 AI 进行多轮对话。支持传入历史消息以保持上下文 (Multi-turn conversation with AI, supports passing historical messages to maintain context)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ai_chat Rate-limited

ai_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": {
    "ai_chat": {
      "limits": [
        {
          "counter": "ai_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 Onion, so you can run agents against it safely.

FAQ

Questions about ai_chat

What does the ai_chat tool do? +

与 AI 进行多轮对话。支持传入历史消息以保持上下文，. It is categorised as a Execute tool in the Onion MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ai_chat? +

Register the Onion MCP server in PolicyLayer and add a rule for ai_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 Onion. Nothing to install.

What risk level is ai_chat? +

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

Can I rate-limit ai_chat? +

Yes. Add a rate_limit block to the ai_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 ai_chat completely? +

Set action: deny in the PolicyLayer policy for ai_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 ai_chat? +

ai_chat is provided by the Onion MCP server (onion-ai/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.