Enables automated creation and generation of Anki flashcard decks with rich CSS templates, media asset embedding, and secure file handling through genanki integration
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Genanki MCP Server create a Spanish vocabulary deck with audio pronunciations"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Automated Anki deck generation service built with genanki and the Model Context Protocol (MCP).
Focuses on dependable deck creation, strict media sandboxing, and keeping the workflow lean—nothing more.
Streamable MCP HTTP tool that plugs into any MCP-compliant client
Agents can craft rich CSS templates and embed media assets safely
Temporary download links (default expiry 600 seconds) for .apkg retrieval
Media path sandbox prevents out-of-scope file access and orphaned assets
Related MCP server: Anki MCP Server with ElevenLabs Support
anki_mcp/
├── anki_tools/ # genanki utility wrapper
│ └── genanki_tool.py
├── server/ # MCP + HTTP entrypoints
│ ├── anki_models.py # Pydantic request/response models
│ └── anki_server.py # FastMCP / Starlette server
├── temp_anki_decks/ # Temporary .apkg exports
├── .envexample # Environment variable template
├── pyproject.toml # uv / pip project definition
└── uv.lockgit clone https://github.com/Epiphany-0312/genanki-mcp.git
cd genanki-mcpPython ≥ 3.13
Dependency management via uv (recommended) or pip
# With uv (recommended)
uv sync
# Or with pip
python -m venv .venv
.venv\Scripts\activate # PowerShell
pip install -r requirements.txtDuplicate .envexample to .env and adjust as needed.
Variable | Description | Default |
| Uvicorn/FastMCP listening port |
|
| Public IP/host used to compose download links |
|
| Optional bearer token protecting tool access | (empty) |
If TOKEN is omitted, the service skips authentication. Set it in production environments.
uv run python -m server.anki_server
# or
python -m server.anki_serverFastMCP exposes the tool at http://0.0.0.0:<PORT>/anki and temporary downloads at http://0.0.0.0:<PORT>/downloads.
Connect with any MCP-capable client. By default the MCP endpoint listens on http://127.0.0.1:10099/anki.
Cherry Studio example configuration and workflow:
MIT License
This server cannot be deployed
Deploy AI-generated HTML/CSS/JS to instant public HTTPS URLs from any MCP-compatible agent.
Generate images and PDFs from HTML/CSS, live websites, and reusable templates.
Host static HTML pages, generate PDFs, screenshots, scrape JS sites, run sandboxed JavaScript.
Upload AI-written HTML presentations and manage expiring, revocable share links over OAuth.
