swarm_chat · Mcp Swarm MCP: Risk & Policy

WHAT IT DOES

What swarm_chat does on Mcp Swarm

AI agents invoke swarm_chat to trigger actions in Mcp Swarm. 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 swarm_chat needs a policy

This tool triggers external API calls to multiple LLM providers (Qwen, MiniMax, GLM, Kimi), which constitutes executing external operations with side effects including API usage costs and data transmission to third-party services. It falls under Execute rather than Write since it invokes external systems rather than creating/modifying local data.

From the tool's definition 自动选择最合适的模型并调用你的 API 进行对话 (automatically selects the most suitable model and calls your API for conversation)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

swarm_chat Rate-limited

swarm_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": {
    "swarm_chat": {
      "limits": [
        {
          "counter": "swarm_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 Mcp Swarm, so you can run agents against it safely.

FAQ

Questions about swarm_chat

What does the swarm_chat tool do? +

根据任务内容自动选择最合适的模型并调用你的 API 进行对话。支持 8 个模型：qwen3.5-plus、qwen3-max-2026-01-23、qwen3-coder-next、qwen3-coder-plus、MiniMax-M2.5、glm-5、glm-4.7、kimi-k2.5。. It is categorised as a Execute tool in the Mcp Swarm MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on swarm_chat? +

Register the Mcp Swarm MCP server in PolicyLayer and add a rule for swarm_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 Mcp Swarm. Nothing to install.

What risk level is swarm_chat? +

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

Can I rate-limit swarm_chat? +

Yes. Add a rate_limit block to the swarm_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 swarm_chat completely? +

Set action: deny in the PolicyLayer policy for swarm_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 swarm_chat? +

swarm_chat is provided by the Mcp Swarm MCP server (moselu/mcp-swarm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.