bullet-mcp-server
Provides physics simulation capabilities using PyBullet, enabling 3D physics world creation, object loading, force application, and state monitoring through MCP protocol.
README
PyBullet MCP Server
A Model Context Protocol (MCP) server that provides physics simulation capabilities using PyBullet. This server allows external applications to interact with PyBullet physics simulations through standardized MCP protocol endpoints.
Features
šÆ Physics Simulation: Create and manage 3D physics simulations š§ Object Management: Load URDF objects, set colors, apply forces ā” Real-time Control: Step simulation, set velocities, reset poses š State Monitoring: Query simulation status and object information š² Scene Generation: Create random test scenes with multiple objects
Components
Resources
The server provides access to simulation data through custom bullet:// URIs:
bullet://simulation/status- Current simulation state and parametersbullet://simulation/objects- List of all objects in the simulationbullet://simulation/physics_params- Physics world configurationbullet://objects/{id}- Individual object details and current state
Tools
The server implements comprehensive physics simulation tools:
-
create_simulation: Initialize or reset the physics world
- Configure gravity, time step, real-time mode
- Choose between GUI or headless (DIRECT) mode
-
load_object: Load URDF objects into the simulation
- Support for standard PyBullet objects (cube, sphere, r2d2, etc.)
- Configurable position, orientation, scaling, and name
-
set_object_color: Change object appearance
- Set RGBA color values for visual customization
-
apply_force: Apply forces to objects
- World frame or link frame force application
- Configurable force vector and application point
-
set_velocity: Control object motion
- Set linear and angular velocities directly
-
step_simulation: Advance the physics simulation
- Single or multiple simulation steps
- Respects real-time constraints
-
get_object_info: Query detailed object state
- Position, orientation, velocities, and metadata
-
create_random_scene: Generate test scenarios
- Configurable number of objects and area size
- Random positions, orientations, and colors
-
reset_object_pose: Reset object positions
- Precise position and orientation control
Installation
- Clone or download this MCP server
- Install dependencies using uv:
uv sync --dev --all-extras
Usage
With Claude Desktop
Add to your Claude Desktop configuration:
macOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"bullet-mcp-server": {
"command": "uv",
"args": [
"--directory",
"/path/to/bullet-mcp-server",
"run",
"bullet-mcp-server"
]
}
}
}
Development
Run the server directly:
uv run bullet-mcp-server
Or in development mode:
uv run python -m bullet_mcp_server.server
Example Usage
Once connected to Claude Desktop, you can:
-
Create a physics world: "Create a new physics simulation with standard gravity"
-
Load objects: "Load a cube at position [0, 0, 2] and a sphere at [1, 1, 3]"
-
Apply physics: "Apply a force of [10, 0, 0] to the cube and step the simulation 100 times"
-
Create scenes: "Create a random scene with 15 objects in a 10x10 area"
-
Monitor state: "Show me the current positions and velocities of all objects"
Development
The server is built using:
- PyBullet: Physics simulation engine
- MCP SDK: Model Context Protocol implementation
- uv: Fast Python package manager
- Python 3.8+: Modern Python features
Project Structure
bullet-mcp-server/
āāā src/bullet_mcp_server/
ā āāā __init__.py
ā āāā server.py # Main MCP server implementation
āāā .github/
ā āāā copilot-instructions.md
āāā .vscode/
ā āāā mcp.json # VS Code MCP configuration
āāā pyproject.toml # Project configuration
āāā README.md
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
This project is open source. See the license file for details.
Support
For issues and questions:
- Check the PyBullet documentation: https://pybullet.org/
- Review MCP protocol docs: https://modelcontextprotocol.io/
- Open an issue in this repository
]
}
}
</details>
<details> <summary>Published Servers Configuration</summary>
"mcpServers": {
"bullet-mcp-server": {
"command": "uvx",
"args": [
"bullet-mcp-server"
]
}
}
</details>
Development
Building and Publishing
To prepare the package for distribution:
- Sync dependencies and update lockfile:
uv sync
- Build package distributions:
uv build
This will create source and wheel distributions in the dist/ directory.
- Publish to PyPI:
uv publish
Note: You'll need to set PyPI credentials via environment variables or command flags:
- Token:
--tokenorUV_PUBLISH_TOKEN - Or username/password:
--username/UV_PUBLISH_USERNAMEand--password/UV_PUBLISH_PASSWORD
Debugging
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm with this command:
npx @modelcontextprotocol/inspector uv --directory /home/borges/dev/bullet-mcp-server run bullet-mcp-server
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
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.