chat · Ros MCP: Risk & Policy

WHAT IT DOES

What chat does on Ros

AI agents invoke chat to trigger actions in Ros. 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 needs a policy

This tool acts as an LLM-driven orchestrator that can trigger any of the sibling tools on the server, including navigation commands, motion commands, and map saving. Since it can autonomously execute actions on physical robots based on natural language interpretation, and sibling tools include destructive/high-risk operations like cancel_navigation and send_motion_command, the effective blast radius is critical.

From the tool's definition 'call robot tools when needed' — this tool interprets natural language and autonomously invokes sibling tools including navigate_to_poses, send_motion_command, cancel_navigation, and save_map on physical autonomous mobile robots

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

chat Rate-limited

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": {
    "chat": {
      "limits": [
        {
          "counter": "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 Ros, so you can run agents against it safely.

FAQ

Questions about chat

What does the chat tool do? +

Interpret natural-language operator requests with the configured LLM bridge, call robot tools when needed, and return a Korean operator-facing response. It is categorised as a Execute tool in the Ros 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? +

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

What risk level is chat? +

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

Can I rate-limit chat? +

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

Set action: deny in the PolicyLayer policy for 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 chat? +

chat is provided by the Ros MCP server (reidlo5135/ros-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.