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

arXiv: https://arxiv.org/abs/2506.03548 · HTML: https://mlsanity.com/paper/2506.03548/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 39 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## Builds on (most cited first, 13 of 13)

- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [CoLight: Learning Network-level Cooperation for Traffic Signal Control](https://mlsanity.com/paper/1905.05717/) (2019)
- [LLMLight: Large Language Models as Traffic Signal Control Agents](https://mlsanity.com/paper/2312.16044/) (2023)
- [Open-TI: Open Traffic Intelligence with Augmented Language Model](https://mlsanity.com/paper/2401.00211/) (2023)
- [Exploration of LLM Multi-Agent Application Implementation Based on LangGraph+CrewAI](https://mlsanity.com/paper/2411.18241/) (2024)
- [ChatSUMO: Large Language Model for Automating Traffic Scenario Generation in Simulation of Urban MObility](https://mlsanity.com/paper/2409.09040/) (2024)
- [LLM-Assisted Light: Leveraging Large Language Model Capabilities for Human-Mimetic Traffic Signal Control in Complex Urban Environments](https://mlsanity.com/paper/2403.08337/) (2024)
- [Smart Mobility Digital Twin Based Automated Vehicle Navigation System: A Proof of Concept](https://mlsanity.com/paper/2402.12682/) (2024)
- [CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control](https://mlsanity.com/paper/2503.11739/) (2025)
- [RoboCar: A Rapidly Deployable Open-Source Platform for Autonomous Driving Research](https://mlsanity.com/paper/2405.03572/) (2024)
- [Deploying scalable traffic prediction models for efficient management in real-world large transportation networks during hurricane evacuations](https://mlsanity.com/paper/2406.12119/) (2024)

## Built on by (most cited first, 3 of 3)

- [AgentSUMO: An Agentic Framework for Interactive Simulation Scenario Generation in SUMO via Large Language Models](https://mlsanity.com/paper/2511.06804/) (2025)
- [SimSkill: A Self-Evolving LLM Agent for Skill and Knowledge Accumulation in Traffic Simulation](https://mlsanity.com/paper/2609.03753/) (2026)
- [Decoupled Intelligence: A Multi-Agent LLM Framework for Controllable Traffic Scenario Generation in SUMO](https://mlsanity.com/paper/2605.27685/) (2026)

## Abstract (arXiv)

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.