Record ROS data to a bag file
AI agents use record_bag to create or update resources in ROS 2 MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ROS 2 MCP Server environment.
This tool records live ROS 2 data to a bag file on disk, which is a Write operation (creating/writing a file). It could have high blast radius if misused: continuous recording could fill disk storage, capture sensitive sensor/system data, or interfere with system resources. It is not Destructive (does not delete data) nor Execute (does not run arbitrary commands), though it does trigger an external recording process.
From the tool's definition 'Record ROS data to a bag file' — creates a new bag file and writes ROS topic/message data into it
Attacks that exploit this kind of access
Record ROS data to a bag file. It is categorised as a Write tool in the ROS 2 MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ROS 2 MCP Server MCP server in PolicyLayer and add a rule for record_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.
record_bag is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the record_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.
Set action: deny in the PolicyLayer policy for record_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.
record_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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →