summarize_run

THE RISK

Low Risk

Why summarize_run needs a policy

This tool reads and aggregates existing NONMEM run outputs (control stream, .ext, and .lst files) to produce a summary. It retrieves and combines data without modifying, executing, or deleting anything.

From the tool's definition Generate a comprehensive summary... by combining control stream, .ext, and .lst results

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

POLICY

How to control summarize_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 summarize_run:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "summarize_run": {}
  }
}

summarize_run is read-only, so it stays allowed — but 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.

CAP 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 Execute submit_run Submit a NONMEM run (async). Returns a job ID for polling. Requires NONMEM installation. Read compare_models Compare multiple NONMEM runs by OFV, delta-OFV, parameter counts, and AIC. Accepts a list

All 22 Nonmem tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about summarize_run

What does the summarize_run tool do? +

Generate a comprehensive summary of a NONMEM run by combining control stream, .ext, and .lst results. It is categorised as a Read tool in the Nonmem MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on summarize_run? +

Register the Nonmem MCP server in PolicyLayer and add a rule for summarize_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 summarize_run? +

summarize_run is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit summarize_run? +

Yes. Add a rate_limit block to the summarize_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 summarize_run completely? +

Set action: deny in the PolicyLayer policy for summarize_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 summarize_run? +

summarize_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 →