SUMO-MCP 是一个连接大语言模型 (LLM) 与 Eclipse SUMO 交通仿真的中间件。通过 Model Context Protocol (MCP),它允许 AI 智能体(如 Claude, Cursor, TRAE等)直接调用 SUMO 的核心功能,实现从OpenStreetMap 数据获取、路网生成、需求建模到仿真运行与信号优化的全流程自动化。
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"sumo-mcp": {
"env": {
"SUMO_HOME": "/your/actual/sumo/path",
"PYTHONPATH": "/path/to/sumo-mcp/src"
},
"args": [
"/path/to/sumo-mcp/src/server.py"
],
"command": "/path/to/your/env/python"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
SUMO-MCP 是一个连接大语言模型 (LLM) 与 Eclipse SUMO 交通仿真的中间件。通过 Model Context Protocol (MCP),它允许 AI 智能体(如 Claude, Cursor, TRAE等)直接调用 SUMO 的核心功能,实现从OpenStreetMap 数据获取、路网生成、需求建模到仿真运行与信号优化的全流程自动化。
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
uvx 'git' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked git against OSV.dev.
This server is missing a description. Tools and install config are also missing.If you've used it, help the community.
Add informationBe the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in maps / education
A Model Context Protocol server for searching and analyzing arXiv papers
MCP server for NotebookLM - Let your AI agents (Claude Code, Codex) research documentation directly with grounded, citation-backed answers from Gemini. Persistent auth, library management, cross-client sharing. Zero hallucinations, just your knowledge base.
A MCP server that integrates the Semantic Scholar API and the arXiv API so AI assistants (e.g. Claude Code, Cursor) can search and fetch academic paper metadata.
MCP server that uses arxiv-to-prompt to fetch and process arXiv LaTeX sources for precise interpretation of mathematical expressions in scientific papers.
MCP Security Weekly
Get CVE alerts and security updates for SUMO MCP Server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
SUMO-MCP is a middleware layer connecting Large Language Models (LLMs) with Eclipse SUMO traffic simulation. Through Model Context Protocol (MCP), AI agents (such as Claude, Cursor, and TRAE) can directly call SUMO capabilities for end-to-end automation across OpenStreetMap data retrieval, network generation, demand modeling, simulation execution, and signal optimization.
The system supports both offline workflows (file-based pipelines) and online interaction (real-time TraCI control), covering use cases from macroscopic planning to microscopic control.
API reference: doc/API.md (the single source of truth remains tool registration in src/server.py).
ezdesignX conversion guide: doc/EZDESIGNX_TO_SUMO.md.
Core MCP interfaces are grouped into intuitive tools to simplify common SUMO operations:

manage_network): Generate networks (generate), download OSM data (download_osm), convert formats (convert), and convert ezdesignX v1 JSON/JSONC (convert_ezdesignx). A dedicated convert_ezdesignx_network tool is also available.manage_demand): Generate random trips (generate_random), convert OD matrices (convert_od), and compute routes (compute_routes).optimize_traffic_signals): Includes cycle adaptation (cycle_adaptation) and coordination (coordination). cycle_adaptation outputs SUMO <additional> signal plans (automatically mounted into <additional-files> by workflows).run_simple_simulation) and FCD trajectory analysis (run_analysis).Some aggregated tools accept params.options: list[str], which are appended token-by-token to underlying SUMO binaries/scripts (see "General Conventions" in doc/API.md).
Real-time control via TraCI enables fine-grained closed-loop operations:
control_simulation): Connect (connect), step (step), and cleanly disconnect (disconnect).query_simulation_state): Fetch active vehicle IDs (vehicle_list), per-vehicle variables (vehicle_variable), and global simulation statistics.Built-in end-to-end workflows (run_workflow) for research and engineering tasks:
sim_gen_eval): One-shot pipeline: "generate network -> generate demand -> route computation -> simulation -> analysis".
grid_number (aliases: grid_size, size), sim_seconds (aliases: steps, duration, end_time), output_dirsignal_opt): Full pipeline: "baseline simulation -> optimization ->