Parse NONMEM table output files (SDTAB, PATAB, etc.) and compute summary statistics for key columns (CWRES, PRED, IPRED, ETAs).
AI agents call read_nm_tables 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.
This tool retrieves and analyzes existing NONMEM output files (SDTAB, PATAB tables) to extract summary statistics. It performs read-only operations on diagnostic data without side effects, capability to modify underlying data, or trigger external operations. The analysis of pharmacometric model diagnostics presents minimal risk even if misused by an AI agent.
From the tool's definition Tool description explicitly states it 'Parse[s] NONMEM table output files' and 'compute[s] summary statistics' on existing outputs. The verbs 'parse' and 'compute' indicate data retrieval and analysis with no modification, creation, or deletion of data.
Documented attack patterns abuse exactly the kind of access read_nm_tables gives an agent:
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_nm_tables:
{
"version": "1",
"default": "deny",
"tools": {
"read_nm_tables": {}
}
}read_nm_tables is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Parse NONMEM table output files (SDTAB, PATAB, etc.) and compute summary statistics for key columns (CWRES, PRED, IPRED, ETAs). It is categorised as a Read tool in the Nonmem MCP Server, which means it retrieves data without modifying state.
Register the Nonmem MCP server in PolicyLayer and add a rule for read_nm_tables: 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.
read_nm_tables is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the read_nm_tables 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 read_nm_tables. 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.
read_nm_tables 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.
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.