gurobi/mcp repository overview

⁠Quick reference

Maintained by: Gurobi Optimization⁠

Where to get help: Gurobi Support⁠, Gurobi Documentation⁠

⁠Supported tags and respective Dockerfile links

• latest⁠

When building a production application, we recommend using an explicit version number instead of the latest tag. This way, you are in control of the upgrade process of your application.

⁠Quick reference (cont.)

Supported architectures: linux/amd64, linux/arm64

Gurobi images:

• gurobi/optimizer⁠: Gurobi Optimizer (full distribution)
• gurobi/python⁠: Gurobi Optimizer (Python API only)
• gurobi/python-example⁠: Gurobi Optimizer example in Python with a WLS license
• gurobi/modeling-examples⁠: Optimization modeling examples (distributed as Jupyter Notebooks)
• gurobi/compute⁠: Gurobi Compute Server
• gurobi/manager⁠: Gurobi Cluster Manager
• gurobi/mcp⁠: Gurobi Intelligence MCP Server

⁠What is gurobi/mcp?

The Gurobi Intelligence MCP Server provides AI-powered assistance for optimization tasks through the Model Context Protocol (MCP)⁠. It enables AI assistants like Claude to interact with Gurobi optimization tools, providing intelligent help with model building, debugging, and optimization workflows.

Important: Gurobi Intelligence credentials are required. Obtain your credentials from the Gurobi Intelligence Hub⁠.

⁠How to use this image?

⁠Getting Started

⁠Prerequisites

1. Gurobi Intelligence Credentials: Obtain your credentials (Access ID and Secret, or license file) from the Gurobi Intelligence Hub⁠.
2. Volume Mounting: Mount your project directory (e.g., $HOME/work) to /workspace. Set GRB_MCP_MOUNT to match the host path for automatic path translation.

⁠Running the MCP Server

⁠Using Environment Variables (Recommended)

$ export GRB_INTELLIGENCE_ACCESS_ID=your_access_id
$ export GRB_INTELLIGENCE_SECRET=your_secret
$ export GRB_MCP_MOUNT=$HOME/work

$ docker run -d --name gurobimcp -p 61095:61095 \
    -e GRB_INTELLIGENCE_ACCESS_ID \
    -e GRB_INTELLIGENCE_SECRET \
    -v $GRB_MCP_MOUNT:/workspace \
    -e GRB_MCP_MOUNT \
    gurobi/mcp:latest

⁠Using a License File

$ export GRB_LICENSE_INTELLIGENCE_FILE=$HOME/gurobi-intelligence.lic
$ export GRB_MCP_MOUNT=$HOME/work

$ docker run -d --name gurobimcp -p 61095:61095 \
    -v $GRB_LICENSE_INTELLIGENCE_FILE:/opt/gurobi/gurobi-intelligence.lic \
    -v $GRB_MCP_MOUNT:/workspace \
    -e GRB_MCP_MOUNT \
    gurobi/mcp:latest

⁠Windows with Docker Desktop

set GRB_INTELLIGENCE_ACCESS_ID=your_access_id
set GRB_INTELLIGENCE_SECRET=your_secret
set GRB_MCP_MOUNT=%USERPROFILE%\work

docker run -d --name gurobimcp -p 61095:61095 ^
  -e GRB_INTELLIGENCE_ACCESS_ID ^
  -e GRB_INTELLIGENCE_SECRET ^
  -v %GRB_MCP_MOUNT%:/workspace ^
  -e GRB_MCP_MOUNT ^
  gurobi/mcp:latest

Note: The server automatically handles Windows path formats. Only one project directory is supported—mount a parent directory if you need access to multiple folders.

⁠Configuring AI Assistants

Once the MCP server is running (on port 61095), configure your AI assistant to connect to it.

⁠Claude Desktop and Claude Code

Using CLI (Recommended):

claude mcp add -t http gurobi-mcp http://localhost:61095/api/v1/agent/mcp

Manual Configuration: Add to your config file:

• Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS/Linux) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
• Claude Code: ~/.claude/config.json

{
  "mcpServers": {
    "gurobi-mcp": {
      "url": "http://localhost:61095/api/v1/agent/mcp",
      "transport": "http"
    }
  }
}

After configuration, restart Claude to connect to the Gurobi Intelligence tools.

⁠GitHub Copilot (VS Code)

Add to your MCP configuration file (~/Library/Application Support/Code/User/mcp.json on macOS/Linux or %APPDATA%\Code\User\mcp.json on Windows):

{
  "servers": {
    "gurobi-mcp": {
      "type": "http",
      "url": "http://localhost:61095/api/v1/agent/mcp",
      "headers": {
        "Accept": "text/event-stream"
      }
    }
  },
  "inputs": []
}

Restart VS Code to connect to the Gurobi Intelligence MCP server.

⁠License

By downloading and using this image, you agree with the End-User License Agreement⁠ for the Gurobi software contained in this image.

As with all Docker images, these likely also contain other software which may be under other licenses (such as Bash, etc from the base distribution, along with any direct or indirect dependencies of the primary software being contained).

As for any pre-built image usage, it is the image user's responsibility to ensure that any use of this image complies with any relevant licenses for all software contained within.