π¦
Grid World Simulation MCP Demo
A simple demo of AI agent simulation in a 2D grid world using FastMCP
0 installs
Trust: 34 β Low
Science
Ask AI about Grid World Simulation MCP Demo
Powered by Claude Β· Grounded in docs
I know everything about Grid World Simulation MCP Demo. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Loading tools...
Reviews
Documentation
GridWorld Agent Demo
This project simulates a simple virtual environment where an AI agent interacts with a 2D grid world using tools exposed via FastMCP. The agent can observe its surroundings, move around, pick up objects, and combine them using recipes to create new items β all governed by external LLM prompts via MCP.
Features
- π§ Agent with stateful inventory and position
- πΊοΈ Grid-based world with emojis representing objects
- π§° Tooling via MCP for
observe,move,pickup,drop,combine - π¦ Recipe system for object interaction (e.g. making tea)
- β‘ Streamlit UI for visualization
- π Auto-refresh on state changes
Getting Started
-
Install dependencies:
pip install -r requirements.txt -
Start the streamlit UI:
streamlit run ui/app.py -
Configure your MCP server. E.g. for Claude:
"grid_world_server": { "command": "uv", "args": [ "--directory", "C:\\path\\to\\project\\root\\", "run", "mcp_server.py" ] }
