Get the FREE Ultimate OpenClaw Setup Guide →

Jij

MCP server provide JijModeling Assistant Tools

Installation
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio jij-inc-jij-mcp-server uv --directory <YOUR PATH>/jij-mcp-server run jij_mcp/server.py

How to use

The Jij MCP Server provides tools for mathematical optimization using JijModeling alongside quantum computing tasks with Qiskit. It exposes JijModeling guidance and validation utilities to help you craft correct optimization models, as well as Qiskit migration guides, API references, and tutorials to assist with quantum circuit design and execution. Use the JijModeling tools to learn syntax, check for common issues, and get best-practice recommendations for building optimization models. Use the Qiskit tooling to migrate between versions, explore API references, and access IBM Quantum Learning Hub tutorials to implement quantum-enhanced optimization workflows within a single MCP server environment.

How to install

Prerequisites:

  • Python 3.8+ and pip
  • Git
  • (Optional) Docker if you prefer containerized deployment
  • Access to the internet to install dependencies

Install steps:

  1. Clone the repository: git clone <repository-url> cd jij-mcp-server

  2. Set up a Python virtual environment (recommended): python -m venv venv

    macOS/Linux

    source venv/bin/activate

    Windows

    venv\Scripts\activate

  3. Install dependencies from requirements.txt (if provided): pip install -r requirements.txt

  4. Configure the MCP server (see configuration snippet in README): Create or edit the settings file to include: { "mcpServers": { "jij": { "command": "uv", "args": [ "--directory", "<YOUR PATH>/jij-mcp-server", "run", "jij_mcp/server.py" ] } } }

  5. Run the server using the configured command (example from README): uv --directory <YOUR PATH>/jij-mcp-server run jij_mcp/server.py

  6. (Optional) If you prefer Docker, follow the Docker configuration in the README to start the container instead.

Note: If you encounter missing dependencies, install them via pip as shown in your requirements file or install specific packages as needed (e.g., qiskit, jij-modeling related libs).

Additional notes

Tips and common issues:

  • Ensure the --directory path points to the correct server workspace where jij_mcp/server.py resides.
  • If using Docker, ensure the image ghcr.io/jij-inc/jij-mcp-server:latest is accessible and you are on a network that allows pulling images.
  • For Qiskit tooling, confirm you have compatible Python versions and required Qiskit packages installed in your environment.
  • If you modify the server code or configuration, restart the MCP server to apply changes.
  • Environment variables can be used to customize paths or API keys for IBM Quantum services; document and supply them in the environment when launching the server if applicable.

Related MCP Servers

Sponsor this space

Reach thousands of developers