submit_run

THE RISK

High Risk

Why submit_run needs a policy

This tool triggers execution of a NONMEM pharmacometric modeling job on external software. It launches an external computation process whose effects depend on the model arguments supplied. This falls under Execute as it runs an external program/process.

From the tool's definition Submit a NONMEM run (async). Returns a job ID for polling. Requires NONMEM installation.

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

POLICY

How to control submit_run

PolicyLayer is an MCP gateway — it sits between your AI agents and Nonmem, and nothing reaches the server without passing your rules. This is the rule we recommend for submit_run:

policy.json

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

submit_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 Nonmem — 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 Nonmem tools

Destructive cancel_run Cancel a running NONMEM job. Execute execute_psn_bootstrap Run bootstrap using PsN (async). Returns job ID for polling. Requires PsN + NONMEM. Execute execute_psn_vpc Run VPC using PsN (async). Returns job ID for polling. Requires PsN + NONMEM. Execute run_diagnostics Run comprehensive post-run diagnostics: boundary checks, condition number, shrinkage, prec Execute simulate_mrgsolve Run a simulation using mrgsolve (R). No NONMEM needed. Provide model code or model file pa Execute generate_vpc_data Generate VPC data using mrgsolve + vpc R package. No NONMEM needed. Requires observed data Read compare_models Compare multiple NONMEM runs by OFV, delta-OFV, parameter counts, and AIC. Accepts a list Read parse_control_stream Parse a NONMEM control stream (.ctl/.mod) into structured components: $THETA, $OMEGA, $SIG

All 22 Nonmem 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 Nonmem → 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 submit_run

What does the submit_run tool do? +

Submit a NONMEM run (async). Returns a job ID for polling. Requires NONMEM installation. It is categorised as a Execute tool in the Nonmem MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on submit_run? +

Register the Nonmem MCP server in PolicyLayer and add a rule for submit_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 Nonmem. Nothing to install.

What risk level is submit_run? +

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

Can I rate-limit submit_run? +

Yes. Add a rate_limit block to the submit_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 submit_run completely? +

Set action: deny in the PolicyLayer policy for submit_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 submit_run? +

submit_run is provided by the Nonmem MCP server (sueinchoi/nonmem-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Nonmem tool call.

Start from Nonmem, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →