AI agents invoke navigate_to_poses 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.
This tool executes external operations (robot navigation) with side effects that depend on supplied arguments (target poses). While not destructive or financial, it meets the Execute category definition: 'runs code, shell commands, browser actions, or triggers external operations whose effects depend on arguments.' The severity is high because misuse could cause physical robots to navigate to unsafe locations,…
From the tool's definition Sends a Nav2 NavigateToPoses command over MQTT to control autonomous mobile robots (AMRs). This triggers real-world motion and navigation actions in physical robots whose effects depend entirely on the pose arguments provided.
Attacks that exploit this kind of access
Send a Nav2 NavigateToPoses-style command over MQTT. 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.
Register the Ros MCP server in PolicyLayer and add a rule for navigate_to_poses: 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.
navigate_to_poses is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the navigate_to_poses 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 navigate_to_poses. 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.
navigate_to_poses 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.
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 →