nonmem-mcp-server

Overview Schema Source Related Servers Discussions Admin

generate_vpc_data

Generate Visual Predictive Check (VPC) data for pharmacometric models using mrgsolve and vpc R packages without requiring NONMEM software.

Instructions

Generate VPC data using mrgsolve + vpc R package. No NONMEM needed. Requires observed data and model.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "observed_data_path": "<observed_data_path>"
    },
    "name": "generate_vpc_data"
  }
}

Input Schema

Name	Required	Description
`model_code`	No	Inline mrgsolve model code
`model_file`	No	Path to mrgsolve .mod file
`observed_data_path`	Yes	Path to observed dataset (required)
`n_sim`	No	Number of simulations (default: 200)
`seed`	No	Random seed
`pred_corr`	No	Prediction-corrected VPC
`stratify_on`	No	Stratification variable
`output_dir`	No	Directory for output files

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Mar 30, 2026

TDQS

A3.7/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. Fails to disclose critical behavioral traits: whether output is returned or written to disk (despite 'output_dir' parameter implying file I/O), side effects, or computational intensity. Only discloses input requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences with zero waste. Front-loaded with core function, followed by key differentiator (No NONMEM), then prerequisites. Every clause provides essential selection or usage information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 8 parameters and no output schema/annotations, description covers the essential domain context (R packages used) and input requirements. Missing disclosure of output behavior (file generation vs return values) and error conditions, leaving gaps for a tool of this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, providing comprehensive parameter documentation. Description adds minimal semantic value beyond schema, though it correctly notes that a 'model' is required (semantic constraint) even though the JSON schema only marks 'observed_data_path' as required. Baseline 3 appropriate given schema quality.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States specific verb ('Generate'), resource ('VPC data'), and implementation method ('mrgsolve + vpc R package'). The phrase 'No NONMEM needed' effectively distinguishes it from sibling tool 'execute_psn_vpc' and signals the alternative technology stack.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear prerequisites ('Requires observed data and model') and differentiates from NONMEM-based alternatives ('No NONMEM needed'). Lacks explicit 'when to use X instead' guidance, but the technology constraint provides implicit selection criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.