AspenPlus MCP Server
Enables AI assistants to interact with Aspen Plus process simulations through a standardized MCP interface, supporting simulation control, data access, and flowsheet manipulation.
README
AspenPlus MCP Server
MCP (Model Context Protocol) server for Aspen Plus process simulation integration. This server enables AI assistants to interact with Aspen Plus simulations through a standardized interface.
Features
- Process Simulation Control: Open, run, and manage Aspen Plus simulations
- Data Access: Read and write stream properties, block parameters, and simulation results
- Flowsheet Manipulation: Create, delete, and connect equipment blocks and streams (enhanced mode)
- Equipment Support: Mixer, Heater, Flash2, Radfrac, DSTWU, RPLUG, RCSTR, RYIELD
- AI Integration: Connect Claude and other AI assistants to Aspen Plus
Requirements
- Python 3.10 or higher
- Windows OS (for Aspen Plus COM interface)
- Aspen Plus installed
- pywin32 package
Installation
- Clone this repository:
git clone <repository-url>
cd AspenPlus-MCP-Server
- Create a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
- Install the package:
pip install -e .
Usage
Running the Server
python -m aspenplus_mcp.server
Available Tools
Basic Mode Tools
open_simulation- Open an Aspen Plus simulation file (setuse_enhanced: false)run_simulation- Run the current simulationget_value- Get a value from the simulation using a node pathset_value- Set a value in the simulationclose_simulation- Close the current simulation
Enhanced Mode Tools (requires use_enhanced: true)
place_block- Add a new equipment block to the flowsheetdelete_block- Remove an equipment block from the flowsheetplace_stream- Add a new stream to the flowsheetconnect_stream- Connect a stream to a block portsave_simulation- Save the simulation to file
Example Node Paths
# Stream temperature
\\Data\\Streams\\S1\\Output\\TEMP_OUT\\MIXED\\MIXED
# Block parameter
\\Data\\Blocks\\B1\\Input\\TEMP
# Component flow rate
\\Data\\Streams\\S1\\Output\\MOLEFLOW\\MIXED\\WATER
Development
Install development dependencies:
pip install -e ".[dev]"
Run tests:
pytest
Format code:
black src/
Configuration with Claude Desktop
Add to your Claude Desktop config file:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"aspenplus": {
"command": "C:\\path\\to\\AspenPlus-MCP-Server\\venv\\Scripts\\python.exe",
"args": [
"-m",
"aspenplus_mcp.server"
]
}
}
}
Important Notes:
- Use the full absolute path to your virtual environment's Python executable
- On Windows, use double backslashes (
\\) in paths or forward slashes (/) - After editing the config file, restart Claude Desktop completely
- The MCP server will start automatically when Claude Desktop launches
Usage Examples
Basic Mode - Reading/Writing Values
# Open simulation in basic mode
open_simulation(filepath="C:/simulations/myprocess.bkp", use_enhanced=False)
# Read stream temperature
get_value(path="\\Data\\Streams\\S1\\Output\\TEMP_OUT\\MIXED\\MIXED")
# Set feed temperature
set_value(path="\\Data\\Streams\\FEED\\Input\\TEMP", value=25.0)
# Run simulation
run_simulation()
Enhanced Mode - Flowsheet Editing
# Open simulation in enhanced mode
open_simulation(filepath="C:/simulations/myprocess.bkp", use_enhanced=True)
# Add a mixer block
place_block(block_name="MIX-01", equipment_type="Mixer")
# Add streams
place_stream(stream_name="STREAM-1", stream_type="MATERIAL")
place_stream(stream_name="STREAM-2", stream_type="MATERIAL")
# Connect streams to mixer
connect_stream(block_name="MIX-01", stream_name="STREAM-1", port_name="IN1")
connect_stream(block_name="MIX-01", stream_name="STREAM-2", port_name="IN2")
# Save changes
save_simulation()
Credits
This project integrates the AspenPlus-Python-Interface by Richard ten Hagen for advanced flowsheet manipulation capabilities.
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。