SUMO
Connects LLMs to Eclipse SUMO traffic simulation, enabling AI agents to automate traffic network generation, demand modeling, signal optimization, simulation execution, and real-time TraCI control through natural language.
What is SUMO?
SUMO is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to connects llms to eclipse sumo traffic simulation, enabling ai agents to automate traffic network generation, demand modeling, signal optimization, simulation execution, and real-time traci control thr...
Connects LLMs to Eclipse SUMO traffic simulation, enabling AI agents to automate traffic network generation, demand modeling, signal optimization, simulation execution, and real-time TraCI control through natural language.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Connects LLMs to Eclipse SUMO traffic simulation, enabling A
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx sumo-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use SUMO
The SUMO MCP Server connects LLMs like Claude to Eclipse SUMO (Simulation of Urban MObility), the open-source traffic simulation platform, enabling natural-language control of complex traffic engineering workflows. Through its MCP tools, AI agents can generate road networks from scratch or from OpenStreetMap data, model traffic demand, optimize signal timing, execute simulations, analyze trajectory output, and perform real-time TraCI control — all via conversational prompts. It is aimed at researchers, urban planners, and traffic engineers who want to automate SUMO workflows without writing Python scripts manually.
Prerequisites
- Eclipse SUMO installed with the SUMO_HOME environment variable set (download from https://eclipse.dev/sumo/)
- Python 3.10 or later with uv installed
- The SUMO-MCP-Server repository cloned locally
- An MCP-compatible client such as Claude Desktop
Install Eclipse SUMO
Download and install Eclipse SUMO from https://eclipse.dev/sumo/. After installation, set the SUMO_HOME environment variable to the SUMO installation directory.
# Verify SUMO is installed
sumo --version
# Export SUMO_HOME (add to your shell profile)
export SUMO_HOME="/path/to/sumo"Clone the SUMO-MCP-Server repository
Clone the server repository to your local machine.
git clone https://github.com/XRDS76354/SUMO-MCP-Server.git
cd SUMO-MCP-ServerInstall Python dependencies
Install the server and its dependencies using uv.
pip install uv
uv sync
source .venv/bin/activate # Linux/macOS
# .venv\Scripts\activate # WindowsTest the server starts correctly
Run the server script directly to verify it starts without errors before adding it to your MCP client.
SUMO_HOME="/path/to/sumo" PYTHONPATH="/path/to/SUMO-MCP-Server/src" python src/server.pyAdd to your MCP client configuration
Edit your claude_desktop_config.json to register the SUMO MCP server. Use absolute paths for all values — relative paths are not supported.
{
"mcpServers": {
"sumo-mcp": {
"command": "/absolute/path/to/.venv/bin/python",
"args": ["/absolute/path/to/SUMO-MCP-Server/src/server.py"],
"env": {
"SUMO_HOME": "/absolute/path/to/sumo",
"PYTHONPATH": "/absolute/path/to/SUMO-MCP-Server/src"
}
}
}
}Restart your MCP client and verify
Fully quit and reopen Claude Desktop. Ask Claude to list available SUMO tools or generate a simple test network to confirm the connection is working.
SUMO Examples
Client configuration
Add this to claude_desktop_config.json, replacing all paths with absolute paths to your SUMO installation and SUMO-MCP-Server clone.
{
"mcpServers": {
"sumo-mcp": {
"command": "/absolute/path/to/.venv/bin/python",
"args": ["/absolute/path/to/SUMO-MCP-Server/src/server.py"],
"env": {
"SUMO_HOME": "/absolute/path/to/sumo",
"PYTHONPATH": "/absolute/path/to/SUMO-MCP-Server/src"
}
}
}
}Prompts to try
Use these prompts in Claude Desktop to control SUMO simulations through natural language.
- "Create a 3x3 grid road network, simulate 100 seconds, and report the average vehicle speed"
- "Download the road network for downtown Berlin from OpenStreetMap and run a traffic simulation"
- "Generate random trip demand for my network and compute routes"
- "Optimize signal timing for my intersection network to minimize average wait time"
- "Connect to the running simulation and monitor vehicle v_0 speed each step, alerting if it drops below 5 m/s"
- "List available built-in RL training scenarios and train the intersection scenario for 5 episodes"Troubleshooting SUMO
SUMO_HOME not set — server fails to find SUMO executables
Set SUMO_HOME to the absolute path of your SUMO installation directory (the folder containing 'bin/', 'data/', and 'tools/'). Add it to the env block in your MCP config, and also export it in your shell profile for CLI use.
Server starts but tools fail with Python import errors
Ensure PYTHONPATH is set to the src/ directory of the SUMO-MCP-Server repository in your MCP config. Also verify the virtual environment's Python binary is used as the command, not the system Python.
TraCI connection errors during real-time simulation control
TraCI requires SUMO to be started with the --remote-port flag to accept connections. Ensure the simulation is started through the MCP server's simulation tools rather than externally, or that the port numbers match.
Frequently Asked Questions about SUMO
What is SUMO?
SUMO is a Model Context Protocol (MCP) server that connects llms to eclipse sumo traffic simulation, enabling ai agents to automate traffic network generation, demand modeling, signal optimization, simulation execution, and real-time traci control through natural language. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install SUMO?
Follow the installation instructions on the SUMO GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with SUMO?
SUMO works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is SUMO free to use?
Yes, SUMO is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
SUMO Alternatives — Similar Coding Agents Servers
Looking for alternatives to SUMO? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up SUMO in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use SUMO?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.