Gurobi MCP
Enables AI applications to solve optimization problems including linear programming, mixed-integer programming, and quadratic programming using the Gurobi solver installed on the local device.
README
About
What is a MCP server?
Model Context Protocol (MCP) is a open protocol that standardizes how Large Language Model (LLM) applications, such as IDEs and AI, connect with external data sources, tools, and prompts. Any application that is MCP compatible can use any MCP server to connect to external sources. This allows AI applications to improve its context with access to external data sources or tools. MCP servers can include databases, research paper search tools, etc. that extends the context available to a LLM.
What is the Gurobi MCP?
This is a MCP server that connects a AI application to use gurobi solver on device to solve optimization problems formulated by the LLM. The MCP server runs on device and uses gurobi software installed on device
What problem types can I solve?
The MCP server accounts for the following problem types:
- Linear Programming (LP)
- Mixed-Integer Linear Programming (MILP)
- Quadratic Programming (QP) – convex and non-convex
- Mixed-Integer QP (MIQP)
- Quadratically Constrained Programming (QCP) – convex and non-convex
- Mixed-Integer QCP (MIQCP)
How to setup the server in Claude desktop?
Note: If Claude desktop is not already downloaded, download it here: https://claude.ai/download
- Clone the repository
git clone https://github.com/KKonuru/GurobiMCP.git
or download the project as a zip and unzip in your repo directory
- Enter the project directory, create a virtual environment, and install packages listed in requirements.txt
cd GurobiMCP
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
- Copy the full path of your python interpreter in .venv folder and the main.py file in your package. Then open claude desktop and open settings.
In settings click on the developer tab on the left side of the page. Then click open edit config which will open file explorer.
Open the file named "claude_desktop_config.json". Here modify the file such as stated below but replace the command and args with the two paths copied earlier.
{
"mcpServers": {
"gp-solver": {
"command": "/Path/to/gurobiMCP/.venv/bin/python",
"args": [
"/Path/to/gurobiMCP/main.py"
]
}
}
}
- Restart Claude desktop and the tool should appear after clicking the second icon on the left.
The prompt also appears when clicking the + icon
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.