SUMO-MCP: Leveraging the Model Context Protocol for Autonomous Traffic Simulation and Optimization

2025-06-04

AI Summary

Existing traffic simulation tools (e.g., SUMO) rely on labor-intensive manual workflows, resulting in high entry barriers and poor reproducibility. To address this, we propose SUMO-MCP—a novel platform that pioneers a natural language–driven simulation paradigm based on the Model Context Protocol (MCP), enabling zero-code, dynamic orchestration of the SUMO toolchain. Our method automates end-to-end simulation pipelines: it constructs road networks from OpenStreetMap, generates traffic demand from OD matrices or stochastic models, executes batch simulations under diverse signal control strategies, and performs automated comparative analysis and congestion detection. By tightly integrating a natural language interface, encapsulated SUMO engine, geospatial data parsing, and intelligent scheduling, SUMO-MCP significantly enhances accessibility, result reliability, and scenario construction efficiency. The platform is open-source and has been validated across multiple real-world urban road networks.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Sampling/Simulation-based Search
• Natural Language Processing: Summarization

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Traffic simulation tools, such as SUMO, are essential for urban mobility research. However, such tools remain challenging for users due to complex manual workflows involving network download, demand generation, simulation setup, and result analysis. In this paper, we introduce SUMO-MCP, a novel platform that not only wraps SUMO' s core utilities into a unified tool suite but also provides additional auxiliary utilities for common preprocessing and postprocessing tasks. Using SUMO-MCP, users can issue simple natural-language prompts to generate traffic scenarios from OpenStreetMap data, create demand from origin-destination matrices or random patterns, run batch simulations with multiple signal-control strategies, perform comparative analyses with automated reporting, and detect congestion for signal-timing optimization. Furthermore, the platform allows flexible custom workflows by dynamically combining exposed SUMO tools without additional coding. Experiments demonstrate that SUMO-MCP significantly makes traffic simulation more accessible and reliable for researchers. We will release code for SUMO-MCP at https://github.com/ycycycl/SUMO-MCP in the future.

Problem

• Simplifying complex manual workflows in traffic simulation tools
• Automating traffic scenario generation and demand creation
• Enhancing simulation accessibility and reliability for researchers

Innovation

• Unified tool suite wrapping SUMO core utilities
• Natural-language prompts for traffic scenario generation
• Flexible custom workflows without additional coding