AI agents invoke create_run to trigger actions in Opentrons 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.
This tool initiates execution of a protocol run on a physical robot, triggering real-world operations (liquid handling, movement, etc.). It is not merely writing data — it causes the robot to execute physical actions, making it Execute category. Misuse could result in equipment damage, sample loss, or lab accidents, hence high severity.
From the tool's definition Create a new protocol run on the robot
Documented attack patterns abuse exactly the kind of access create_run gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Opentrons MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_run:
{
"version": "1",
"default": "deny",
"tools": {
"create_run": {
"limits": [
{
"counter": "create_run_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}create_run 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.
Create a new protocol run on the robot. It is categorised as a Execute tool in the Opentrons MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Opentrons MCP Server MCP server in PolicyLayer and add a rule for create_run: 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 Opentrons MCP Server. Nothing to install.
create_run 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 create_run 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 create_run. 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.
create_run is provided by the Opentrons MCP Server MCP server (yerbymatey/opentrons-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Opentrons MCP Server, 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.
14 Opentrons MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.