mcpField
G
Genesis MCP Server

Genesis MCP Server

Local
github.com/dustlandScience & Education5Updated 84w ago

About Genesis MCP Server

Genesis MCP Server connects MCP clients to Genesis World simulations and their visualization features. It uses stdio because visualization requires a local runtime and is not supported over network transports.

Key features

  1. 01Run Genesis World simulations
  2. 02Support simulation code and parameters
  3. 03Provide world information resources
  4. 04Launch visualization through a local stdio client

Use cases

  1. 01Run a Genesis World simulation from an MCP client
  2. 02Inspect world information exposed as a resource
  3. 03View simulations in the local visualization window

MCP support

Exposes a run_simulation tool and world_info://{name} resources to MCP clients over stdio. Network transports are not supported for visualization.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README
Genesis

Genesis MCP Server

A Model Context Protocol (MCP) server for Genesis World simulations with visualization support.

Quick Start

For the fastest way to get started with visualization:

# Run the simplified setup script (only installs what's needed)
./setup.sh

# Run the stdio client (opens a visualization window)
./examples/stdio_client.py

This will directly start a Genesis World simulation with visualization using stdio transport.

Transport Method: stdio

This server uses stdio transport which is required for Genesis World visualization features. The visualization components require a local runtime and cannot work over network transports.

Setup

Prerequisites
  • Python 3.8+
  • uv package manager (pip install uv)
  • npm (optional, for MCP Inspector)
Installation
Linux/macOS
# Clone the repository
git clone https://github.com/username/genesis-mcp.git
cd genesis-mcp

# Run the setup script
./setup.sh

# Activate the virtual environment
source .venv/bin/activate
Windows
# Clone the repository
git clone https://github.com/username/genesis-mcp.git
cd genesis-mcp

# Run the setup script
setup.bat

# Activate the virtual environment
.venv\Scripts\activate.bat
Manual Installation with uv

If you prefer to install dependencies manually:

  1. Create a virtual environment:

    uv venv .venv
    source .venv/bin/activate  # Linux/macOS
    .venv\Scripts\activate.bat  # Windows
    
  2. Install dependencies from lock file:

    uv pip install -r requirements.lock
    uv pip install -e .
    uv pip install genesis==0.2.1 --no-deps
    
  3. Install MCP Inspector (optional):

    npm install -g @modelcontextprotocol/[email protected]
    

Running the Server

# Run with stdio transport (required for visualization)
./start.sh


### Using with the MCP Inspector

To use with the MCP Inspector for debugging:

```bash
# In one terminal, start the inspector
mcp-inspector

# In another terminal, start the server with stdio transport
python server.py

Configure the MCP Inspector with:

  • Transport Type: STDIO
  • Command: python
  • Arguments: server.py

Available Resources

World Info

Get information about Genesis World features:

world_info://{name}

Available Tools

Run Simulation

Run a Genesis World simulation with provided code and parameters:

run_simulation

MCP Client

The repository includes stdio client for visualization:

# Run a simulation with Genesis World visualization
./examples/stdio_client.py

Happy hacking!

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.