nonmem-mcp-server
An MCP server for NONMEM pharmacometric modeling that provides structured access to model parsing, execution, and results analysis. It enables users to perform diagnostics, manage PsN workflows, and translate models to mrgsolve for PK simulations through natural language.
README
nonmem-mcp-server
MCP (Model Context Protocol) server for NONMEM pharmacometric modeling workflows. Gives Claude (and any MCP-compatible client) structured access to NONMEM models, results, and simulation tools.
Features
Phase 1: Parsing & Analysis (no NONMEM needed)
read_ext_file— Parse .ext files for parameter estimates, SEs, OFV, condition numberread_lst_file— Extract termination status, shrinkage, covariance step resultsparse_control_stream— Structural parsing of .ctl/.mod files (THETAs, OMEGAs, $EST options)read_nm_dataset— Dataset summary: subjects, observations, missing valuesread_nm_tables— Parse SDTAB/PATAB with statistics for CWRES, ETAs, PREDcompare_models— Multi-run OFV comparison with delta-OFV and AICsummarize_run— Combined .ctl + .ext + .lst summarylist_runs— Scan project directories for NONMEM runs
Phase 2: Execution & Diagnostics
submit_run— Start NONMEM runs (async, fire-and-poll pattern)check_run_status— Monitor iteration progress via .ext fileget_run_results— Retrieve parsed results when completecancel_run— Kill running NONMEM jobsrun_diagnostics— Automated checks: boundary, condition number, shrinkage, RSEexecute_psn_vpc— Run VPC via PsN (predcorr, stratify, lloq options)execute_psn_bootstrap— Run bootstrap via PsN (BCa, stratify)check_psn_status— Monitor PsN job progressparse_psn_results— Parse existing PsN output directories (no installation needed)check_nonmem_setup— Detect NONMEM, PsN, R installation status
Phase 3: Simulation (no NONMEM needed)
translate_to_mrgsolve— Convert NONMEM .ctl/.mod to mrgsolve model codesimulate_mrgsolve— Run PK simulations via mrgsolve (R)generate_vpc_data— Generate VPC data using mrgsolve + vpc R packagecheck_r_setup— Check R and package availability
Prompts
review_model— Model review checklistinterpret_results— Pharmacological interpretationtroubleshoot_run— Diagnose run failuressuggest_next_model— Suggest next modeling stepswrite_methods_section— Draft publication Methods text
Requirements
- Python 3.12+
- uv (recommended) or pip
Optional
- NONMEM — Required for
submit_run(commercial license) - PsN — Required for
execute_psn_vpc,execute_psn_bootstrap - R with
mrgsolve,vpc,dplyr— Required for simulation tools
Installation
git clone https://github.com/sueinchoi/nonmem-mcp-server.git
cd nonmem-mcp-server
uv sync
Usage with Claude Code
claude mcp add -s user nonmem -- \
uv run --directory /path/to/nonmem-mcp-server python -m nonmem_mcp
With NONMEM installed:
claude mcp add -s user \
-e NONMEM_NMFE_PATH=/opt/NONMEM/nm75/run/nmfe75 \
nonmem -- \
uv run --directory /path/to/nonmem-mcp-server python -m nonmem_mcp
Verify:
claude mcp list
# nonmem: ... - ✓ Connected
Usage with Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"nonmem": {
"command": "uv",
"args": ["run", "--directory", "/path/to/nonmem-mcp-server", "python", "-m", "nonmem_mcp"],
"env": {
"NONMEM_NMFE_PATH": "/opt/NONMEM/nm75/run/nmfe75"
}
}
}
}
Examples
# Summarize a NONMEM run
"Summarize the run in /path/to/run001/"
# Compare covariate models
"Compare OFV across all models in the covariate analysis directory"
# Diagnose a failed run
"Why did this run fail? Check /path/to/run.lst"
# Translate to mrgsolve for simulation
"Convert my NONMEM model to mrgsolve and run a VPC"
Capability Matrix
| Feature | No NONMEM | + NONMEM | + PsN |
|---|---|---|---|
| Parse .ext/.lst/.ctl | ✓ | ✓ | ✓ |
| Model comparison | ✓ | ✓ | ✓ |
| Diagnostics | ✓ | ✓ | ✓ |
| mrgsolve simulation | ✓ | ✓ | ✓ |
| mrgsolve VPC | ✓ | ✓ | ✓ |
| NONMEM execution | ✗ | ✓ | ✓ |
| PsN VPC | ✗ | ✗ | ✓ |
| PsN Bootstrap | ✗ | ✗ | ✓ |
| Parse PsN results | ✓ | ✓ | ✓ |
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。