Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words

AgentSUMO

by mw-jeongversion 0.1.3i★ 11iRuns on your computerRepository ↗
Registry nameio.github.mw-jeong/agentsumo-mcp

How to install

What it does

MCP server for LLM-driven SUMO traffic simulation, scenario design, and result analysis.

  • Connects Runs on your computer
  • Account or key No key needed · 1 setting to fill in (SUMO_HOME)
  • Category Design, images & audio

Use together with

Skills that teach the AI this kind of work; they work alongside this one

impeccable

The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.

by pbakaus★ 112,5441 skills

Skill · How-to guide

diagram-design

Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, Qoder, and Pi. 45 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.

by cathrynlavery★ 68,0691 skills

Skill · How-to guide

frontend-slides

Create beautiful slides on the web using a coding agent's frontend skills

by zarazhangrui★ 32,5141 skills

Skill · How-to guide

Why it ranks here

Lists are ordered by a usage score (out of 100) built from these parts

Popularity13/80GitHub stars or weekly downloads: the larger counts 60, the smaller 20
Freshness12/12Full marks for a release or code change within 30 days
Still answering0/8The cloud endpoint answered at the last check
Usage score25/100

Quality: Passed 3/3 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)

Install

Pick the AI app you use, then copy the settings.

Let your AI install it with one sentence

Please install AgentSUMO. Follow https://mcp.popnx.com/i/mw-jeong-agentsumo-mcp.md, show me the commands and wait for my OK before running them.

Paste it into an AI that can work on your computer (such as Claude Code or Cursor). It reads our steps, shows you the commands and waits for your OK. No key, no sign-up. · See the full text your AI reads

Passed 3/3 checks · Runs on your computer · ✓ Commands checked Nov 17, 2026

First: which AI do you use?

Pick your app and the steps appear below.

Works with Claude, with some setup first

1 setting(s) to fill in (SUMO_HOME) · Install Python (uv) on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone

Let AI install it

Copy this message into a Claude chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server AgentSUMO for Claude on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "agentsumo": { "command": "uvx", "args": [ "agentsumo-mcp" ], "env": { "SUMO_HOME": "your-value" } } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) For SUMO_HOME, leave "your-value" in place and tell me to paste the real value myself into the file or the app’s field. Never ask me to type a key in chat. 5) Do what we agreed, then check that the AgentSUMO tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install uv (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    uv --version
    • A version number such as uv … = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required

    Open the uv download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version

    Install once; it works for everything that needs uv

  2. Fill in 1 setting(s)

    These are program settings, not keys. No sign-up needed; fill them in as the maker describes.

    • SUMO_HOME Absolute path to the local SUMO installation directory (must contain bin/; tools/ may sit directly inside it or under share/sumo/).

    Descriptions are as written by the maker.

  3. Open the Claude desktop app’s settings file

    SettingsDeveloperEdit Config

  4. Paste these settings and save the file

    {
      "mcpServers": {
        "agentsumo": {
          "command": "uvx",
          "args": [
            "agentsumo-mcp"
          ],
          "env": {
            "SUMO_HOME": "your-value"
          }
        }
      }
    }
  5. Quit Claude and open it again

  6. Try it

    Use AgentSUMO and tell me what you can do for me, then show me one thing

    ✓ If Claude says it is using AgentSUMO or shows a AgentSUMO tool in the answer, you are connected

1 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • AGENTSUMO_MCP_OUTPUT_BASE Base directory for simulation outputs (networks, trips, results). Defaults to the current working directory, or ~/agentsumo-output when it is not writable.

Descriptions are as written by the maker.

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

ChatGPT cannot connect AgentSUMO yet

AgentSUMO runs on your computer, but ChatGPT can only connect servers that run on the web

What you can do instead

A · Use an app that can connect AgentSUMO

  • 1 setting(s) to fill in (SUMO_HOME) · Install Python (uv) on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
  • 1 setting(s) to fill in (SUMO_HOME) · Install Python (uv) on your computer first (one time)
  • 1 setting(s) to fill in (SUMO_HOME) · Install Python (uv) on your computer first (one time)
  • 1 setting(s) to fill in (SUMO_HOME) · Install Python (uv) on your computer first (one time)

B · Others in Design, images & audio that work with ChatGPT

Picked from the most used in the same category, only ones that connect by address with no key

Works with Claude Code, with some setup first

1 setting(s) to fill in (SUMO_HOME) · Install Python (uv) on your computer first (one time)

Let AI install it

Copy this message into a Claude Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server AgentSUMO for Claude Code on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): claude mcp add --scope user agentsumo --env SUMO_HOME=your-value -- uvx agentsumo-mcp 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) For SUMO_HOME, leave "your-value" in place and tell me to paste the real value myself into the file or the app’s field. Never ask me to type a key in chat. 5) Do what we agreed, then check that the AgentSUMO tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install uv (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    uv --version
    • A version number such as uv … = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required

    Open the uv download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version

    Install once; it works for everything that needs uv

  2. Fill in 1 setting(s)

    These are program settings, not keys. No sign-up needed; fill them in as the maker describes.

    • SUMO_HOME Absolute path to the local SUMO installation directory (must contain bin/; tools/ may sit directly inside it or under share/sumo/).

    Descriptions are as written by the maker.

  3. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: open PowerShell

  4. Paste this command and press Enter

    claude mcp add --scope user agentsumo --env SUMO_HOME=your-value -- uvx agentsumo-mcp
  5. Type /mcp in Claude Code

    You should see AgentSUMO listed as connected

  6. Try it

    Use AgentSUMO and tell me what you can do for me, then show me one thing

    ✓ If Claude Code says it is using AgentSUMO or shows a AgentSUMO tool in the answer, you are connected

1 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • AGENTSUMO_MCP_OUTPUT_BASE Base directory for simulation outputs (networks, trips, results). Defaults to the current working directory, or ~/agentsumo-output when it is not writable.

Descriptions are as written by the maker.

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with Cursor, with some setup first

1 setting(s) to fill in (SUMO_HOME) · Install Python (uv) on your computer first (one time)

Let AI install it

Copy this message into a Cursor chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server AgentSUMO for Cursor on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "agentsumo": { "command": "uvx", "args": [ "agentsumo-mcp" ], "env": { "SUMO_HOME": "your-value" } } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) For SUMO_HOME, leave "your-value" in place and tell me to paste the real value myself into the file or the app’s field. Never ask me to type a key in chat. 5) Do what we agreed, then check that the AgentSUMO tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install uv (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    uv --version
    • A version number such as uv … = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required

    Open the uv download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version

    Install once; it works for everything that needs uv

  2. Fill in 1 setting(s)

    These are program settings, not keys. No sign-up needed; fill them in as the maker describes.

    • SUMO_HOME Absolute path to the local SUMO installation directory (must contain bin/; tools/ may sit directly inside it or under share/sumo/).

    Descriptions are as written by the maker.

  3. Click this button to open Cursor

    Open in Cursor

    Cursor asks you to confirm; click Install

  4. Fill in your key

    In the AgentSUMO settings, SUMO_HOME is empty; add your key and save

  5. Open the AI chat in Cursor in Agent mode

  6. Try it

    Use AgentSUMO and tell me what you can do for me, then show me one thing

    ✓ If Cursor says it is using AgentSUMO or shows a AgentSUMO tool in the answer, you are connected

1 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • AGENTSUMO_MCP_OUTPUT_BASE Base directory for simulation outputs (networks, trips, results). Defaults to the current working directory, or ~/agentsumo-output when it is not writable.

Descriptions are as written by the maker.

Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with VS Code, with some setup first

1 setting(s) to fill in (SUMO_HOME) · Install Python (uv) on your computer first (one time)

Let AI install it

Copy this message into a VS Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server AgentSUMO for VS Code on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "servers": { "agentsumo": { "type": "stdio", "command": "uvx", "args": [ "agentsumo-mcp" ], "env": { "SUMO_HOME": "your-value" } } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) For SUMO_HOME, leave "your-value" in place and tell me to paste the real value myself into the file or the app’s field. Never ask me to type a key in chat. 5) Do what we agreed, then check that the AgentSUMO tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install uv (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    uv --version
    • A version number such as uv … = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required

    Open the uv download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version

    Install once; it works for everything that needs uv

  2. Fill in 1 setting(s)

    These are program settings, not keys. No sign-up needed; fill them in as the maker describes.

    • SUMO_HOME Absolute path to the local SUMO installation directory (must contain bin/; tools/ may sit directly inside it or under share/sumo/).

    Descriptions are as written by the maker.

  3. Click this button to open VS Code

    Open in VS Code

    VS Code asks you to confirm; click Install

  4. Fill in your key

    In the AgentSUMO settings, SUMO_HOME is empty; add your key and save

  5. Open the AI chat in VS Code in Agent mode

  6. Try it

    Use AgentSUMO and tell me what you can do for me, then show me one thing

    ✓ If VS Code says it is using AgentSUMO or shows a AgentSUMO tool in the answer, you are connected

1 optional setting(s) (works without them)

The command above works without these. Add them only if you want to change something, following the maker’s description.

  • AGENTSUMO_MCP_OUTPUT_BASE Base directory for simulation outputs (networks, trips, results). Defaults to the current working directory, or ~/agentsumo-output when it is not writable.

Descriptions are as written by the maker.

Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.

See every app that uses MCP →

JSON settings are under “For developers” below

Stuck? Ask people who use AgentSUMO💬 Discussion →
For developers: Terminal commands and JSON settings

Installed on your computer

Claude Code

claude mcp add --scope user agentsumo --env SUMO_HOME=your-value -- uvx agentsumo-mcp

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "agentsumo": {
      "command": "uvx",
      "args": [
        "agentsumo-mcp"
      ],
      "env": {
        "SUMO_HOME": "your-value"
      }
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "agentsumo": {
      "command": "uvx",
      "args": [
        "agentsumo-mcp"
      ],
      "env": {
        "SUMO_HOME": "your-value"
      }
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "agentsumo": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "agentsumo-mcp"
      ],
      "env": {
        "SUMO_HOME": "your-value"
      }
    }
  }
}

Values you fill in

  • SUMO_HOME required env
    Absolute path to the local SUMO installation directory (must contain bin/; tools/ may sit directly inside it or under share/sumo/).
  • AGENTSUMO_MCP_OUTPUT_BASE env
    Base directory for simulation outputs (networks, trips, results). Defaults to the current working directory, or ~/agentsumo-output when it is not writable.

Descriptions are as written by the maker.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

At a glance

Downloads per weeki
34/wk
Connection
Runs on your computer
Latest versioni
0.1.3
Published to registryi
Nov 17, 2026
Code last changedi
Nov 17, 2026
Maker
mw-jeong
Packages
pypi: agentsumo-mcp
Registry status
Active

Which apps can use it

Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.

Run on your computer in

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

All apps, with pros and cons →

Related guides

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 19, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account urban-ai-institute, which owns the repo

  • ✓ Pass

    Still maintained

    Code last changed 2 days ago

  • ✓ Pass

    Has a licence

    Uses MIT

  • – Not applicable

    Endpoint responds

    This one runs on your computer; there is no internet endpoint

  • – Not applicable

    Sign-in with OAuth

    Runs on your computer and uses local settings instead

  • … Not checked yet

    No hidden instructions in tool descriptions

    Runs on your computer; we can only read tool lists from internet endpoints

Published vulnerabilities (OSV.dev)

Not checked yet

What we check → · JSON

Makers: ask for a re-check or report wrong info
For makers: add a badge to your README

If you made this, paste this code into your README. The badge links back to this page.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/mw-jeong-agentsumo-mcp.svg)](https://mcp.popnx.com/en/servers/mw-jeong-agentsumo-mcp)

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in to post

User reviews

No reviews yet

Sign in to write a review

Compared with others in Design, images & audioi

  • More stars than 93% of the other 3275 servers in this category
  • Published to the registry more recently than 94% of the other 3275 servers in this category
  • Basic checks equal to or better than 99% of the other 3275 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is AgentSUMO safe?

It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed 2 days ago, and the latest version (0.1.3) reached the registry 2 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.

What can I use instead?

In the same category: HyperFrames by HeyGen, Pascal 3D Editor, draw.io, Figma MCP Server, Remocn: Remotion MCP server

Similar alternatives

Same category, other makers, commands already checked. Official ones first, then by stars.

Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

HyperFrames by HeyGen

Official HyperFrames by HeyGen: the best AI video editor in chat. Captions, motion graphics, MP4.

by heygen-comWidely used★ 86.4K Stars for the whole repoUpdated yesterday

Runs in the cloud✓ heygen.com

Pascal 3D Editor

Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.

by pascalorgWidely used↓ 1K/wk★ 25.6K Stars for the whole repoUpdated yesterday

Computer or cloud✓ service owner · pascal.app

draw.io

Create draw.io diagrams in chat from Mermaid or XML, shown live and interactive. 10,000+ shapes.

by jgraphWidely used★ 5.9KUpdated 2 days ago

Runs in the cloud✓ service owner · draw.ioTried by the PopNx team

Figma MCP Server

Figma’s official server gives AI your design data so it can turn designs into code or describe them accurately. Connects to Figma’s cloud.

by figmaWidely used★ 2.2KUpdated 13 months ago

Runs in the cloud✓ service owner · mcp.figma.com
Compared with similar ones
This one
AgentSUMO
HyperFrames by HeyGenPascal 3D Editordraw.ioFigma MCP ServerRemocn: Remotion MCP server
Runs whereInstalls on your computerRuns in the cloud, nothing to installCloud or install on your computerRuns in the cloud, nothing to installRuns in the cloud, nothing to installRuns in the cloud, nothing to install
Needs a keyNoNoNoNoNoNo
Add with + in ClaudeNoYesNoNoYesNo
Basic checks3/34/45/54/44/44/4
LicenseMITApache-2.0MITApache-2.0–MIT
PriceNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registry

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

AgentSUMO

An Agentic Framework for Interactive Simulation Scenario Generation in SUMO via Large Language Models

[Documentation](https://agentsumo.readthedocs.io) · Installation · Tools · Schema · Tutorials


Overview

AgentSUMO lets non-expert stakeholders design, execute, and analyze SUMO traffic simulations through natural-language interaction. The Planner Agent translates abstract policy questions into executable simulation plans, drives them via the Model Context Protocol (MCP), and surfaces results through a web dashboard.

  • Conversational scenario design — describe a policy question, get a runnable simulation
  • Policy experiments — road closures, lane reductions, signal optimization, demand changes
  • Cross-scenario analysis — SQL-based comparison across runs, with auto-generated HTML reports
  • Web dashboard — geospatial visualization, time-series charts, and trip replay

Demo

*Web interface: conversational planning panel, scenario list, and live simulation status.*

*Geospatial visualization: per-edge metrics, congestion overlays, and trip replay on the 2.5D basemap.*

Architecture

User (natural language)

| v Planner Agent (Claude LLM, Interactive Planning Protocol) | +--> AgentSUMO MCP Client --> AgentSUMO MCP Server (PyPI: agentsumo-mcp) --> SUMO | +--> SQLite MCP Client --> SQLite MCP Server (Anthropic, open source) --> simulations.db | +--> Filesystem MCP Client --> Filesystem MCP Server (Anthropic, open source) --> additional XML files

The reasoning layer (Planner Agent) lives in this repository. The execution layer (agentsumo-mcp) is published to PyPI and installed automatically as a dependency.

Tool Layer

The AgentSUMO MCP Server exposes 26 tools grouped into five capability categories that follow the simulation workflow. Full reference at agentsumo.readthedocs.io/.../tools.

CategoryPurposeRepresentative tools
Scenario GenerationBuild a baseline SUMO simulation: OSM → network → trips → routes → runosm_extract, net_convert, trip_generate, route_generate, sumo_runner
Policy ExperimentationApply infrastructure, demand, and signal-control interventionsedge_edit_tool, reduce_lanes_tool, vehicle_generation_tool, flow_generation_tool, tls_offset_tool, tls_adaptation_tool
Result AnalysisConvert SUMO XML output to SQLite and render HTML reportsxml_to_sqlite_tool, simulation_report_tool
VisualizationRender networks, highlighted edges, and per-edge metric heatmapsvisualize_net_tool, visualize_edge_tool, visualize_policy_target_tool, visualize_edgedata_tool
Utility FunctionsNetwork statistics, routing, road-name ↔ edge-id resolution, OD-coordinate validation, web-search groundingnetwork_summary_tool, route_analysis_tool, validate_od_coordinates_tool, web_search_tool

Installation

Requirements
  • Python 3.12
  • SUMO 1.24 or later (locally installed, with SUMO_HOME set)
  • Node.js 18 or later with npx on PATH, for the Filesystem MCP Server (@modelcontextprotocol/server-filesystem, downloaded by npx on first run). Without it the agent still starts, but cannot read the additional-file guides, write rerouter / VSS / vType files, or inspect Real OD CSVs
  • Anthropic Claude API key (bring-your-own-key)
  • Mapbox access token (web interface only; the CLI does not need it)
  • Internet access: OSM road data comes from the public Overpass API, place names are geocoded with Nominatim, and web_search_tool uses DuckDuckGo
  • Optional: osmium-tool (brew install osmium-tool / sudo apt-get install osmium-tool). Only used when Overpass fails: the server then cuts the area from a Geofabrik .osm.pbf extract
1. Install SUMO

macOS — Download the installer from the Eclipse SUMO downloads page, or use Homebrew. SUMO is not in Homebrew's core formulae; it comes from SUMO's own tap:

brew tap dlr-ts/sumo

brew install sumo

AgentSUMO runs SUMO headless, so the XQuartz setup the Homebrew formula mentions is only needed for `sumo-gui`.

Windows — Download the installer from the Eclipse SUMO downloads page.

Linux (Ubuntu/Debian)

sudo add-apt-repository ppa:sumo/stable

sudo apt-get update sudo apt-get install sumo sumo-tools sumo-doc

2. Set up the Python environment

Install uv:

# macOS / Linux

curl -LsSf https://astral.sh/uv/install.sh | sh

Windows (PowerShell)

powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

Clone the repository, create a virtual environment, and install AgentSUMO:

git clone https://github.com/urban-ai-institute/kra35-prismx-agentsumo.git

cd kra35-prismx-agentsumo

Create a Python 3.12 venv

uv venv --python 3.12

Activate the venv

source .venv/bin/activate # macOS / Linux

.venv\Scripts\activate # Windows

Install AgentSUMO and all dependencies

(this also pulls agentsumo-mcp from PyPI as a dependency)

uv pip install -e .

3. Configure environment variables

AgentSUMO reads API keys and the SUMO path from environment variables. The easiest way is a .env file at the project root:

cp .env.example .env

Open .env in your editor and fill in:

`ANTHROPIC_API_KEY` (required) — Claude API key that drives the Planner Agent. Get one at the Anthropic Console.

ANTHROPIC_API_KEY=[PopNx MCP ตัดค่าที่หน้าตาเหมือนกุญแจออก]

`MAPBOX_TOKEN` (required for the web UI) — used to render the basemap. Get one at the Mapbox access tokens page.

MAPBOX_TOKEN=pk.eyJ1Ijoixxxxxxxxxxxxxxxxxx

`SUMO_HOME` (required) — absolute path to your local SUMO installation. The directory must contain bin/sumo (or bin/sumo.exe on Windows).

# macOS (Homebrew): $(brew --prefix sumo)/share/sumo

SUMO_HOME=/opt/homebrew/opt/sumo/share/sumo

macOS (Eclipse SUMO installer)

SUMO_HOME=/Library/Frameworks/EclipseSUMO.framework/Versions/ /EclipseSUMO # e.g. 1.24.0; use the directory name installed under Versions/

Windows

SUMO_HOME=C:\Program Files (x86)\Eclipse\Sumo

Linux

SUMO_HOME=/usr/share/sumo

`AGENTSUMO_MCP_OUTPUT_BASE` (optional) — override the base directory where the MCP server writes simulation outputs (networks, trips, results). Defaults to the current working directory, or ~/agentsumo-output when that directory is not writable (MCP hosts such as Claude Desktop often start servers in /).

AGENTSUMO_MCP_OUTPUT_BASE=/path/to/your/output/dir
4. Run
# Web interface (opens at http://localhost:8000; needs MAPBOX_TOKEN)

python web.py # python web.py --port 8001 to use another port

CLI mode (type 'help' for commands, 'quit' to exit)

python chat.py

Delete generated simulation outputs (keeps uploads/ and vehicle_types.add.xml)

python clean.py

On start the CLI prints Tools available: N: 26 AgentSUMO tools plus 14 Filesystem tools when Node.js is available. The six SQLite tools are added once a simulation database exists (after the first xml_to_sqlite_tool call).

Simulation outputs go to output/ under the directory you start from (or AGENTSUMO_MCP_OUTPUT_BASE). Start from the repository root so the MCP server runs the checkout's agentsumo_mcp rather than the PyPI copy.

Project Structure

AgentSUMO/

├── agentsumo/ │ ├── agent/ # Planner Agent (Claude orchestrator + prompts) │ ├── client/ # MCP clients (AgentSUMO, SQLite, Filesystem) │ └── core/ # Configuration ├── agentsumo_mcp/ # AgentSUMO MCP Server source (also published to PyPI) │ └── defaults/ # Packaged fixtures (e.g., vehicle_types.add.xml) ├── packaging/mcp/ # PyPI build configuration for agentsumo-mcp ├── web/ # Web interface (FastAPI + Jinja2 templates) ├── docs/ # Sphinx documentation source ├── tests/ # Unit tests ├── assets/ # README images ├── output/ # Runtime artifacts (auto-populated; 8 categories tracked │ # via .gitkeep — simulations/, networks/, trips/, │ # analysis/, reports/, uploads/, visualizations/, additional/) ├── chat.py # CLI entry point ├── clean.py # Deletes generated outputs ├── web.py # Web server entry point └── .env.example # Environment variable template

Use the MCP Server Standalone

The AgentSUMO MCP Server can be used independently from this framework with any MCP-compatible LLM client (Claude Desktop, OpenAI tool clients, Gemini, local LLMs):

pip install agentsumo-mcp

Or via uvx without installing:

uvx agentsumo-mcp

The standalone server provides the 26 AgentSUMO tools only; the Planner Agent, the SQLite MCP Server and the Filesystem MCP Server belong to this framework. It needs SUMO_HOME, and writes outputs under AGENTSUMO_MCP_OUTPUT_BASE (default: the working directory, or ~/agentsumo-output when that is not writable). Claude Desktop (claude_desktop_config.json):

{

"mcpServers": { "agentsumo": { "command": "uvx", "args": ["agentsumo-mcp"], "env": { "SUMO_HOME": "/Library/Frameworks/EclipseSUMO.framework/Versions/Current/EclipseSUMO", "AGENTSUMO_MCP_OUTPUT_BASE": "/Users/you/agentsumo-output" } } } }

The server is registered in the official MCP Registry under io.github.mw-jeong/agentsumo-mcp.

Troubleshooting

SUMO path error — Verify SUMO_HOME in your .env. The directory must contain bin/sumo (or bin/sumo.exe on Windows).

API key error — Verify ANTHROPIC_API_KEY in your .env is set to a valid Claude API key. The Planner Agent will refuse to start without it.

`brew install sumo` says "No available formula" — Add SUMO's tap first: brew tap dlr-ts/sumo.

"Filesystem MCP could not start" warning — Install Node.js 18+ and make sure npx is on PATH. The first start downloads `@modelcontextprotocol/serve

Only the beginning is shown; read the rest in the repo