renpy_mcp_server
MCP Server to build Renpy Games
claude mcp add --transport stdio banjtheman-renpy_mcp_server uv --directory /FULL_PATH_TO_RENPY_MCP_SERVER run renpy-mcp-server \
--env GEMINI_API_KEY="${GEMINI_API_KEY}" \
--env RENPY_SDK_PATH="${RENPY_SDK_PATH}"How to use
This MCP server enables AI-assisted creation of Ren’Py visual novels. It integrates with the MCP framework to generate game assets, write Ren’Py scripts, and build playable web deployments. Through the provided API commands, you can generate backgrounds and character assets (including multiple emotions), compose branching dialogue, and bundle everything into a web-playable version of your visual novel with a live preview.
Core capabilities include: generating 2D assets via Gemini-based image generation, automatic script generation for Ren’Py with dialogue and choices, and a built-in workflow to compile and serve a web version of the game. The server exposes a workflow that lets you create a project, generate assets, write and edit story scripts, build the project, and preview it in a browser. It is designed to be used in conjunction with an MCP client (e.g., Claude Desktop, Cursor) to orchestrate AI-driven game production.
How to install
Prerequisites:
- Python 3.10+ installed on your system
- Git available on your PATH
- Access to a Gemini API key for image generation
- Ren’Py SDK (or ability to download it via the setup script)
Step-by-step installation:
- Clone the repository:
git clone https://github.com/banjtheman/renpy_mcp_server.git
cd renpy_mcp_server
- Run the automated setup (preferred):
./setup.sh
This will install Python dependencies, download the Ren’Py SDK, and set up the web support module. It will also help configure the Gemini API key and create MCP configuration files.
- Test the installation:
./test_setup.sh
- If you prefer manual setup, install dependencies and then run the MCP server using uv:
uv sync
export RENPY_SDK_PATH="/path/to/renpy-sdk" # required if not configured by setup
export GEMINI_API_KEY="your-api-key" # required for image generation
Then start the MCP server via MCP client; details are in the MCP client configuration section of the README.
- Optional: test image generation directly (as shown in the docs):
uv run python test_nano_banana.py
Additional notes
Tips and common issues:
- Ensure GEMINI_API_KEY is set in your environment or in the MCP client configuration under env for the server.
- RENPY_SDK_PATH must point to a valid Ren’Py SDK directory; the setup script can download this automatically.
- The MCP client configuration example uses command "uv" with a directory path; replace /FULL_PATH_TO_RENPY_MCP_SERVER with the absolute path to this repository on your machine.
- Web builds require network access for assets generation and may require additional web dependencies configured by setup.sh.
- If the server does not start automatically when the MCP client connects, verify that the RENPY_SDK_PATH and GEMINI_API_KEY environment variables are exported and accessible to the running process.
- You can create projects, generate assets, write scripts, build, and preview entirely through the MCP workflow described in the README.
Related MCP Servers
iterm
A Model Context Protocol server that executes commands in the current iTerm session - useful for REPL and CLI assistance
mcp
Octopus Deploy Official MCP Server
furi
CLI & API for MCP management
editor
MCP Server for Phaser Editor
DoorDash
MCP server from JordanDalton/DoorDash-MCP-Server
mcp
MCP сервер для автоматического создания и развертывания приложений в Timeweb Cloud