Start an execution for an operation (service call or action goal). For services, returns result directly. For actions, returns execution_id to track progress.
AI agents invoke ros2_medkit_create_execution to trigger actions in Ros2 Medkit. 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 directly executes operations on a ROS 2 system (service calls or action goals), which can trigger physical actuators, system state changes, or other real-world effects depending on the robot/system configuration. The blast radius is high because misuse could cause unintended robot behaviors or system state changes that may be difficult to reverse.
From the tool's definition 'Start an execution for an operation (service call or action goal)' — explicitly triggers execution of ROS 2 operations including service calls and action goals
Documented attack patterns abuse exactly the kind of access ros2_medkit_create_execution gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ros2 Medkit, and nothing reaches the server without passing your rules. This is the rule we recommend for ros2_medkit_create_execution:
{
"version": "1",
"default": "deny",
"tools": {
"ros2_medkit_create_execution": {
"limits": [
{
"counter": "ros2_medkit_create_execution_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}ros2_medkit_create_execution 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.
Free to start. No card required.
Start an execution for an operation (service call or action goal). For services, returns result directly. For actions, returns execution_id to track progress. It is categorised as a Execute tool in the Ros2 Medkit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ros2 Medkit MCP server in PolicyLayer and add a rule for ros2_medkit_create_execution: 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 Ros2 Medkit. Nothing to install.
ros2_medkit_create_execution 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 ros2_medkit_create_execution 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 ros2_medkit_create_execution. 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.
ros2_medkit_create_execution is provided by the Ros2 Medkit MCP server (selfpatch/ros2_medkit_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ros2 Medkit, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
84 Ros2 Medkit tools catalogued and risk-classified — across an index of 43,000+ MCP servers.