Low Risk

read_ext_file

Parse a NONMEM .ext file to extract parameter estimates, standard errors, OFV, eigenvalues, and condition number.

How to control read_ext_file ↓

What read_ext_file does on Nonmem

AI agents call read_ext_file to retrieve information from Nonmem without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why read_ext_file needs a policy

This tool performs read-only operations on existing NONMEM output files. It retrieves and parses data (parameter estimates, standard errors, etc.) without creating, modifying, deleting, executing code, or causing side effects. It is purely informational/analytical in nature, consistent with the Read category.

From the tool's definition Tool description explicitly states 'Parse a NONMEM .ext file to extract parameter estimates, standard errors, OFV, eigenvalues, and condition number.' The verb 'extract' and 'parse' indicate data retrieval without modification.

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

How to control read_ext_file

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 read_ext_file:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "read_ext_file": {}
  }
}

read_ext_file is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Nonmem — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about read_ext_file

What does the read_ext_file tool do? +

Parse a NONMEM .ext file to extract parameter estimates, standard errors, OFV, eigenvalues, and condition number. 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 read_ext_file? +

Register the Nonmem MCP server in PolicyLayer and add a rule for read_ext_file: 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 read_ext_file? +

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

Can I rate-limit read_ext_file? +

Yes. Add a rate_limit block to the read_ext_file 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 read_ext_file completely? +

Set action: deny in the PolicyLayer policy for read_ext_file. 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 read_ext_file? +

read_ext_file 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.

Free to start. No card required.

22 Nonmem tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.