control_run

THE RISK

High Risk

Why control_run needs a policy

This tool executes commands that alter the state of a running protocol on a physical laboratory robot (Opentrons Flex/OT-2). While these actions are technically reversible (pausing/resuming, not destruction), they constitute Execute category because they trigger external operations whose effects depend on the current robot state and protocol.

From the tool's definition Tool name 'control_run' with description 'Control run execution (play, pause, stop, resume)' directly triggers state changes on a physical robot.

Documented attack patterns abuse exactly the kind of access control_run gives an agent:

POLICY

How to control control_run

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 control_run:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "control_run": {
      "limits": [
        {
          "counter": "control_run_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

control_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.

Create a free account and register Opentrons MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Opentrons MCP Server tools

Execute home_robot Home robot axes or specific pipette Execute poll_error_endpoint_and_fix Fetch specific JSON error report and automatically fix protocols Execute create_run Create a new protocol run on the robot Write control_lights Turn robot lights on or off Write upload_protocol Upload a protocol file to an Opentrons robot Read get_api_overview Get high-level overview of the Opentrons HTTP API structure and capabilities Read get_endpoint_details Get comprehensive details about a specific API endpoint Read get_protocols List all protocols stored on the robot

All 14 Opentrons MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Opentrons MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about control_run

What does the control_run tool do? +

Control run execution (play, pause, stop, resume). 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.

How do I enforce a policy on control_run? +

Register the Opentrons MCP Server MCP server in PolicyLayer and add a rule for control_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.

What risk level is control_run? +

control_run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit control_run? +

Yes. Add a rate_limit block to the control_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.

How do I block control_run completely? +

Set action: deny in the PolicyLayer policy for control_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.

What MCP server provides control_run? +

control_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.

Enforce policy on every Opentrons MCP Server tool call.

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.

CHECK YOUR STACK →