CircuitMCP
An MCP server that allows AI assistants to create, modify, and simulate electronic circuits with features for circuit creation, component management, simulation analyses, and schematic generation.
README
CircuitMCP
Circuit simulation capabilities exposed through Anthropic's Model Context Protocol (MCP).
Overview
This project implements an MCP server for circuit simulation, allowing AI assistants to create, modify, and simulate electronic circuits. It uses PySpice for simulation and SchemDraw for generating schematic diagrams.
Features
- Circuit Creation: Create circuits with various electronic components
- Component Management: Add, remove, and update components
- Circuit Simulation: Run operating point, DC, AC, and transient analyses
- Schematic Generation: Generate visual representations of circuits
- UVX Components: Support for Universal Verification Xcomponents (op-amps, etc.)
Installation
Quick Setup (Recommended)
We provide setup scripts that handle all installation steps automatically:
- Linux/macOS:
./setup_circuitmcp.sh - Windows (CMD):
setup_circuitmcp.bat - Windows (PowerShell):
.\setup_circuitmcp.ps1
These scripts will:
- Install required dependencies
- Install NGSpice (or guide you through installation)
- Set up a virtual environment (if desired)
- Install CircuitMCP
- Configure UVX for Cursor and Claude Desktop integration (if available)
Using UVX in Cursor or Claude Desktop
The easiest way to install CircuitMCP is using UVX directly in Cursor or Claude Desktop:
# Install the package from GitHub
uvx install git+https://github.com/amzsaint/circuitmcp.git
# Or install by name once registered
uvx install circuitmcp
# Verify installation
uvx list | grep circuitmcp
Claude Desktop Integration
To use CircuitMCP with Claude Desktop:
-
Install the UVX package:
uvx install circuitmcp -
Create an MCP configuration file (
mcp_config.json):{ "servers": [ { "name": "Circuit Simulator", "command": ["circuitmcp-server", "--host", "127.0.0.1", "--port", "8000"] } ] } -
Start Claude Desktop with MCP configuration:
claude-desktop --mcp-config=mcp_config.json -
In Claude Desktop, you can now use circuit simulation capabilities:
Please create a simple voltage divider circuit with a 9V source and two 10kΩ resistors.
Manual Installation
You can also install manually:
-
Clone the repository:
git clone https://github.com/amzsaint/circuitmcp.git cd circuitmcp -
Install Python dependencies:
pip install -r requirements.txt -
Install the package in development mode:
pip install -e . -
Install NGSpice (required for simulation):
- macOS:
brew install ngspice - Ubuntu:
apt-get install ngspice - Windows: Download from the NGSpice website
- macOS:
Usage
Running the Server
# Using the command-line script
circuitmcp-server
# With options
circuitmcp-server --debug --host 0.0.0.0 --port 8000
Or in Python:
# Import the server
from circuitmcp import mcp
# Run the server
mcp.run(host="127.0.0.1", port=8000)
Client Example
# See examples/mcp_client.py for full examples
from examples.mcp_client import CircuitMCPClient
import asyncio
async def main():
client = CircuitMCPClient()
await client.connect()
# Create a circuit
circuit = await client.create_circuit("My Circuit")
circuit_id = circuit["id"]
# Add components
await client.add_component(circuit_id, "V", ["in", "0"], 5.0)
await client.add_component(circuit_id, "R", ["in", "out"], 1000.0)
# Generate schematic
schematic = await client.generate_schematic(circuit_id)
print(f"Schematic generated: {schematic['filepath']}")
await client.close()
if __name__ == "__main__":
asyncio.run(main())
Cursor Integration
When installed via UVX, CircuitMCP can be used directly in Cursor:
- Open Cursor and type
/install circuitmcpor/install git+https://github.com/amzsaint/circuitmcp.git - Use the package in your Python code:
from circuitmcp import mcp, Circuit - Run the server with
/run circuitmcp-server
Testing
Run the test script to verify functionality:
python -m circuitmcp.test_mcp
Project Structure
circuitmcp/: Main packagemcp_server.py: MCP server implementationcircuit.py: Circuit class implementationmock_mcp.py: Mock MCP SDK implementationtest_mcp.py: Test script
examples/: Example client and usageschematics/: Generated circuit schematics
License
MIT
Note on NGSpice
This project requires NGSpice to be installed on your system for simulation capabilities. The schematic generation will work without NGSpice, but simulation features will be unavailable.
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。