play_bag · ROS 2 MCP Server MCP: Risk & Policy

WHAT IT DOES

What play_bag does on ROS 2 MCP Server

AI agents invoke play_bag to trigger actions in ROS 2 MCP Server. 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 play_bag needs a policy

Playing back a bag file actively publishes messages into the ROS 2 middleware, which can cause real-world effects such as moving robots, actuating hardware, or altering system state. This is an external operation whose effects depend on the bag file's contents and the live system, making it Execute. The blast radius is high because misuse could cause unintended physical robot movement or system disruption.

From the tool's definition 'Play back ROS data from a bag file' — replaying a bag file injects messages into a live ROS 2 system, triggering downstream nodes, actuators, and robot behaviors based on recorded data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

play_bag Rate-limited

play_bag 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": {
    "play_bag": {
      "limits": [
        {
          "counter": "play_bag_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 2 MCP Server, so you can run agents against it safely.

FAQ

Questions about play_bag

What does the play_bag tool do? +

Play back ROS data from a bag file. It is categorised as a Execute tool in the ROS 2 MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on play_bag? +

Register the ROS 2 MCP Server MCP server in PolicyLayer and add a rule for play_bag: 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 2 MCP Server. Nothing to install.

What risk level is play_bag? +

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

Can I rate-limit play_bag? +

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

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

play_bag is provided by the ROS 2 MCP Server MCP server (ranch-hand-robotics/rde-mcp-ros-2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.