Run comprehensive post-run diagnostics: boundary checks, condition number, shrinkage, precision (RSE), convergence warnings. No NONMEM needed.
AI agents invoke run_diagnostics to trigger actions in Nonmem. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes a suite of diagnostic computations (boundary checks, condition number calculation, shrinkage, RSE, convergence analysis) rather than merely reading static data. It triggers an active processing workflow. No data is created or destroyed, but it runs external computations, placing it in Execute.
From the tool's definition 'Run comprehensive post-run diagnostics: boundary checks, condition number, shrinkage, precision (RSE), convergence warnings' — actively runs/executes a diagnostic analysis pipeline
Documented attack patterns abuse exactly the kind of access run_diagnostics 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 run_diagnostics:
{
"version": "1",
"default": "deny",
"tools": {
"run_diagnostics": {
"limits": [
{
"counter": "run_diagnostics_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_diagnostics 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.
Free to start. No card required.
Run comprehensive post-run diagnostics: boundary checks, condition number, shrinkage, precision (RSE), convergence warnings. No NONMEM needed. 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.
Register the Nonmem MCP server in PolicyLayer and add a rule for run_diagnostics: 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.
run_diagnostics is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_diagnostics 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 run_diagnostics. 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.
run_diagnostics 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.