
Fujitsu Social Digital Twin MCP Server
Enables LLMs to access Fujitsu's Digital Rehearsal API through natural language, allowing users to run and analyze simulations of human and social behavior in digital space.
Tools
list_simdata
Returns a complete list of all simulation datasets available in the system, which can be used as inputs for running new simulations.
get_simdata
Retrieves the complete configuration and parameter set for a specific simulation dataset, including region settings, time ranges, and scenario parameters.
analyze_traffic_simulation
Conducts comprehensive analysis on simulation results, providing insights on traffic patterns, bottlenecks, and optimization opportunities for the specified parameters.
compare_scenarios
Performs detailed comparative analysis between two simulation scenarios, highlighting differences in traffic flow, emissions, travel times, and other key metrics.
create_natural_language_simulation_config
Converts a natural language description into a structured simulation configuration, interpreting user requirements into technical parameters for traffic simulation.
create_simulation_from_usecase
指定されたユースケースとアップロードされたファイルからシミュレーションを作成・実行します。
list_simulations
Returns a comprehensive list of all traffic simulations in the system, including their IDs, names, status, and execution timeframes.
start_simulation
Launches a new traffic simulation using the provided simulation dataset configuration, returning the simulation ID and initial status.
get_simulation_result
Retrieves the complete results and output files from a finished traffic simulation, including simulation status and generated result files.
get_metrics
Retrieves comprehensive metrics and analytics data from a completed simulation, including travel statistics, emissions data, and traffic flow information.
README
Fujitsu Social Digital Twin MCP Server
This project integrates Fujitsu's Social Digital Twin and Digital Rehearsal API with the Model Context Protocol (MCP), allowing Large Language Models (LLMs) to access Fujitsu's Digital Rehearsal API through natural language.
<a href="https://glama.ai/mcp/servers/@3a3/fujitsu-sdt-mcp"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@3a3/fujitsu-sdt-mcp/badge" alt="Fujitsu Social Digital Twin Server MCP server" /> </a>
Overview
Fujitsu's Social Digital Twin recreates not only the state of people and objects in the digital space based on real-world data, but also entire economic and social activities. Its core function, "Digital Rehearsal," enables users to simulate human and social behavior in a digital space before implementing measures in the real world, allowing for advance verification of their effects and impacts.
This project uses MCP to bridge the gap between LLMs and the Digital Rehearsal API, enabling users to run simulations and analyze results using natural language.
Key Features
- Retrieve and display simulation lists
- Start simulations
- Retrieve and analyze simulation results
- Manage simulation data
- Analyze traffic simulations
- Compare scenarios
- Generate simulation configurations from natural language
Prerequisites
- Python 3.13 or higher
- Access to Fujitsu API Gateway (API Key)
- MCP-compatible LLM client (e.g., Claude Desktop)
Installation
Installing via Smithery
To install Fujitsu Social Digital Twin Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @3a3/fujitsu-sdt-mcp --client claude
1. Clone the Repository
git clone https://github.com/3a3/fujitsu-sdt-mcp.git
cd fujitsu-sdt-mcp
2. Set Up Environment
Using uv (recommended):
First, install uv:
# Install uv using pip
pip install uv
# Or using curl (Linux/macOS)
curl -sSf https://astral.sh/uv/install.sh | sh
Then, set up your environment with uv:
# Create virtual environment
uv venv
# Activate virtual environment
# Windows:
.venv\Scripts\activate
# Unix/MacOS:
source .venv/bin/activate
# Install dependencies
uv pip install -r requirements.txt
Alternatively, you can use the provided setup script:
# Make the script executable
chmod +x setup.sh
# Run setup
./setup.sh
3. Set Environment Variables
# Windows:
set FUJITSU_API_BASE_URL=https://apigateway.research.global.fujitsu.com/sdtp
set FUJITSU_API_KEY=your_api_key_here
# Unix/MacOS:
export FUJITSU_API_BASE_URL=https://apigateway.research.global.fujitsu.com/sdtp
export FUJITSU_API_KEY=your_api_key_here
Alternatively, you can create a .env
file with the following settings:
FUJITSU_API_BASE_URL=https://apigateway.research.global.fujitsu.com/sdtp
FUJITSU_API_KEY=your_api_key_here
Usage
Starting the MCP Server
python -m fujitsu_sdt_mcp
The server communicates using standard I/O with MCP clients.
Using the Interactive Client
A simple client is also provided for direct interaction with the MCP server:
python client.py
When you start the client, a list of available resources and tools will be displayed, and you can call them from the command line.
Setup with Claude Desktop
To use the server with MCP-compatible LLM clients such as Claude Desktop:
- Open Claude Desktop
- Go to Settings > Developer Settings > Edit Config File
- Add the following settings:
"command": "uvx",
"args": [
"fujitsu-sdt-mcp"
],
"env": {
"FUJITSU_API_BASE_URL": "https://apigateway.research.global.fujitsu.com/sdtp",
"FUJITSU_API_KEY": "your_api_key_here"
}
- Restart Claude Desktop
Resources and Tools
Resources
resource://digital_rehearsal_overview
: Overview of Digital Rehearsal technologyresource://simulation_metrics_explanation
: Explanation of simulation metricsresource://scenario_examples
: Example scenarios
Tools
list_simulations
: Retrieve a list of simulationsstart_simulation
: Start a simulationget_simulation_result
: Retrieve simulation resultsget_metrics
: Retrieve simulation metricslist_simdata
: Retrieve a list of simulation dataget_simdata
: Retrieve simulation dataanalyze_traffic_simulation
: Analyze traffic simulationcompare_scenarios
: Compare scenarioscreate_natural_language_simulation_config
: Generate simulation settings from natural language
Usage Examples
Retrieving a List of Simulations
tool list_simulations
Starting a Simulation
tool start_simulation {"simdataId": "your_simdata_id"}
Analyzing Traffic Simulation
tool analyze_traffic_simulation {"simulationId": "your_simulation_id", "region": "Tokyo", "timeRange": "morning rush hour", "scenario": "traffic optimization"}
Generating Simulation Settings from Natural Language
tool create_natural_language_simulation_config {"description": "I want to run a traffic optimization simulation during morning rush hour in Tokyo"}
Example LLM Interaction
User: I want to run a traffic simulation during morning rush hour in Tokyo
Claude: I can help you run a traffic simulation for Tokyo's morning rush hour. Here's how we can set it up.
First, let's generate simulation settings from your natural language description:
[Tool execution: create_natural_language_simulation_config]
Generated settings:
{
"simulationType": "traffic",
"parameters": {
"region": "Tokyo",
"timeRange": "morning_rush"
},
"name": "traffic_20250416_123045"
}
Next, let's check available simulation data:
[Tool execution: list_simdata]
From this data, I can start a simulation using Tokyo's morning traffic data.
I've selected the appropriate simulation data ID and will start the simulation:
[Tool execution: start_simulation]
The simulation has started. The simulation ID is "sim_12345".
It will take some time for the results to be available. Once complete, I'll analyze them.
(After simulation completes)
Let's analyze the simulation results:
[Tool execution: analyze_traffic_simulation]
Analysis results:
- CO2 emissions: 1,250kg
- Average travel time: 42 minutes
- Total traffic volume: 15,700 vehicles
From these results, I can see that the Shibuya-Shinjuku route experiences particularly severe congestion.
Here are some potential improvements:
1. Optimize traffic signal control
2. Implement one-way traffic on certain roads during specific times
3. Increase public transportation frequency
Would you like to see a more detailed analysis?
Contributing
Please report bugs or feature requests via GitHub Issues. Pull requests are welcome.
License
This project is released under the MIT License. See the LICENSE file for details.
Acknowledgments
- Fujitsu Corporation - Development of Social Digital Twin technology
- Model Context Protocol (MCP) - Enabling seamless integration with LLMs
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.