Get robot state from ROS2 topics.
AI agents call nwo_get_ros2_state to retrieve information from NWO Robotics without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read operation that retrieves robot state information from ROS2 (Robot Operating System 2) topics. While categorized as Read, the severity is elevated to 'medium' rather than 'low' because the queried state data could inform subsequent commands to control physical robots.
From the tool's definition Tool name 'nwo_get_ros2_state' and description 'Get robot state from ROS2 topics' indicate a retrieval operation that queries robot state data without modifying it.
Attacks that exploit this kind of access
Get robot state from ROS2 topics. It is categorised as a Read tool in the NWO Robotics MCP Server, which means it retrieves data without modifying state.
Register the NWO Robotics MCP server in PolicyLayer and add a rule for nwo_get_ros2_state: 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 NWO Robotics. Nothing to install.
nwo_get_ros2_state is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the nwo_get_ros2_state 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 nwo_get_ros2_state. 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.
nwo_get_ros2_state is provided by the NWO Robotics MCP server (redciprianpater/mcp-server-robotics). 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 →