MCP4EDA

v1.0.0Developer Toolsstable

This is the Github Repo for the paper: MCP4EDA: LLM-Powered Model Context Protocol RTL-to-GDSII Automation with Backend Aware Synthesis Optimization. MCP server for a collection of open-source EDA tools

mcp4edamcpai-integration
Share:
89
Stars
0
Downloads
0
Weekly
0/5

What is MCP4EDA?

MCP4EDA is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to this is the github repo for the paper: mcp4eda: llm-powered model context protocol rtl-to-gdsii automation with backend aware synthesis optimization. mcp server for a collection of open-source eda too...

This is the Github Repo for the paper: MCP4EDA: LLM-Powered Model Context Protocol RTL-to-GDSII Automation with Backend Aware Synthesis Optimization. MCP server for a collection of open-source EDA tools

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • This is the Github Repo for the paper: MCP4EDA: LLM-Powered

Use Cases

Automate RTL-to-GDSII EDA workflows with LLM assistance.
Optimize synthesis for backend targets using open-source tools.
Enable AI-driven electronic design automation.
NellyW8

Maintainer

LicenseMIT
Languagejavascript
Versionv1.0.0
UpdatedMay 15, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mcp4eda

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use MCP4EDA

MCP4EDA is an MCP server that integrates open-source Electronic Design Automation (EDA) tools — including Yosys, Icarus Verilog, GTKWave, OpenLane, and KLayout — with large language models, enabling AI-assisted RTL-to-GDSII chip design workflows. It was developed alongside the research paper 'MCP4EDA: LLM-Powered Model Context Protocol RTL-to-GDSII Automation with Backend Aware Synthesis Optimization' and exposes EDA tool capabilities as MCP tools so AI assistants can synthesize Verilog, run simulations, execute ASIC flows, and view layout files on your behalf.

Prerequisites

  • Node.js 18 or later and npm
  • Yosys (brew install yosys or sudo apt-get install yosys)
  • Icarus Verilog (brew install icarus-verilog or sudo apt-get install iverilog)
  • Docker Desktop with OpenLane image (pip install openlane && docker pull efabless/openlane:latest)
  • KLayout for GDSII viewing (brew install --cask klayout or sudo apt install klayout)
1

Clone and build the MCP4EDA server

Clone the mcp-EDA repository, install dependencies, and build the TypeScript project.

git clone https://github.com/NellyW8/mcp-EDA
cd mcp-EDA
npm install
npm run build
2

Install required EDA tools

Install all EDA tools that the server will orchestrate. On macOS use Homebrew; on Ubuntu use apt-get.

# macOS
brew install yosys icarus-verilog
brew install --cask gtkwave klayout

# Ubuntu
sudo apt-get install yosys iverilog gtkwave klayout
3

Install OpenLane via Docker

OpenLane runs inside Docker and is required for the full RTL-to-GDSII ASIC flow. Install the Python CLI and pull the Docker image.

pip install openlane
docker pull efabless/openlane:latest
docker run hello-world  # verify Docker is working
4

Configure Claude Desktop

Add the MCP4EDA server to your Claude Desktop config, ensuring the PATH variable includes all EDA tool binary locations.

{
  "mcpServers": {
    "mcp4eda": {
      "command": "node",
      "args": ["/path/to/mcp-EDA/dist/index.js"],
      "env": {
        "PATH": "/usr/local/bin:/opt/homebrew/bin:/usr/bin:/bin",
        "HOME": "/your/home/directory"
      }
    }
  }
}
5

Restart Claude Desktop and verify

After saving the config file, restart Claude Desktop. Ask Claude to list available tools — you should see tools for synthesis, simulation, and ASIC flow.

MCP4EDA Examples

Client configuration

Claude Desktop configuration for MCP4EDA pointing to the built server on macOS with Homebrew-installed EDA tools.

{
  "mcpServers": {
    "mcp4eda": {
      "command": "node",
      "args": ["/Users/you/mcp-EDA/dist/index.js"],
      "env": {
        "PATH": "/opt/homebrew/bin:/usr/local/bin:/usr/bin:/bin",
        "HOME": "/Users/you"
      }
    }
  }
}

Prompts to try

Example natural language prompts to use with Claude once MCP4EDA is connected.

- "Synthesize this 4-bit counter Verilog module targeting an ice40 FPGA using Yosys"
- "Simulate this adder design with an auto-generated testbench and show me the results"
- "Run the complete RTL-to-GDSII ASIC flow for this module with a 10ns clock period"
- "Open the GDSII layout file from my last OpenLane run in KLayout"
- "Extract the area, power, and timing PPA metrics from the latest OpenLane synthesis report"

Troubleshooting MCP4EDA

Yosys or iverilog not found when the server tries to run synthesis

Add the full path to your Homebrew or system binaries in the PATH env var in your Claude Desktop config. On Apple Silicon, Homebrew installs to /opt/homebrew/bin instead of /usr/local/bin.

OpenLane Docker flow fails with 'Cannot connect to Docker daemon'

Make sure Docker Desktop is running before starting Claude Desktop. Verify with docker ps in a terminal. The OpenLane flow requires the Docker daemon to be accessible.

npm run build fails with TypeScript errors

Run npx tsc after npm run build as specified in the repository instructions, then verify the dist/ directory was created before configuring the server path.

Frequently Asked Questions about MCP4EDA

What is MCP4EDA?

MCP4EDA is a Model Context Protocol (MCP) server that this is the github repo for the paper: mcp4eda: llm-powered model context protocol rtl-to-gdsii automation with backend aware synthesis optimization. mcp server for a collection of open-source eda tools It connects AI assistants to external tools and data sources through a standardized interface.

How do I install MCP4EDA?

Follow the installation instructions on the MCP4EDA GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with MCP4EDA?

MCP4EDA works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is MCP4EDA free to use?

Yes, MCP4EDA is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp4eda": { "command": "npx", "args": ["-y", "mcp4eda"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use MCP4EDA?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides