Frequently Asked Questions (FAQ)

Q: What is the Fujitsu Social Digital Twin? A: The Fujitsu 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.

Q: What is MCP (Model Context Protocol)? A: MCP is an open protocol that standardizes how applications provide context to LLMs. The MCP server acts as a bridge, allowing AI models to access and interact with external data sources and tools.

Q: What are the key features of the Fujitsu Social Digital Twin MCP Server? A: Key features include natural language interaction, digital rehearsal capabilities, comprehensive simulation management, traffic simulation analysis, and seamless integration with MCP-compatible LLM clients.

Q: What are some use cases for this MCP Server? A: Use cases include urban planning, economic policy, supply chain management, healthcare, retail, financial services, and disaster management.

Q: How do I install the Fujitsu Social Digital Twin MCP Server? A: You can install it via Smithery using the command npx -y @smithery/cli install @3a3/fujitsu-sdt-mcp --client claude or manually by cloning the repository and setting up the environment.

Q: What prerequisites are required to use this server? A: You need Python 3.13 or higher, access to the Fujitsu API Gateway (API Key), and an MCP-compatible LLM client (e.g., Claude Desktop).

Q: How do I start the MCP server? A: Run python -m fujitsu_sdt_mcp in your terminal.

Q: How do I use the interactive client? A: Run python client.py for direct interaction with the server.

Q: How do I set up the server with Claude Desktop? A: Open Claude Desktop, go to Settings > Developer Settings > Edit Config File, and add the provided configuration settings.

Q: Where can I find resources and tools documentation? A: The server provides resources such as resource://digital_rehearsal_overview and tools like list_simulations and start_simulation. Details are available in the project documentation.

Q: Can I contribute to this project? A: Yes, please report bugs or feature requests via GitHub Issues. Pull requests are welcome.