Genanki MCP Server
Enables automated generation of Anki flashcard decks with rich CSS templates and media assets. Provides secure deck creation with sandboxed media handling and temporary download links for .apkg files.
README
genanki-mcp
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.
Highlights
- 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
.apkgretrieval - Media path sandbox prevents out-of-scope file access and orphaned assets
Project Layout
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.lock
Quick Start
git clone https://github.com/Epiphany-0312/genanki-mcp.git
cd genanki-mcp
Requirements
- Python ≥ 3.13
- Dependency management via uv (recommended) or
pip
Install Dependencies
# With uv (recommended)
uv sync
# Or with pip
python -m venv .venv
.venv\Scripts\activate # PowerShell
pip install -r requirements.txt
Configure Environment Variables
Duplicate .envexample to .env and adjust as needed.
| Variable | Description | Default |
|---|---|---|
PORT |
Uvicorn/FastMCP listening port | 10099 |
SREVERIP |
Public IP/host used to compose download links | 127.0.0.1 |
TOKEN |
Optional bearer token protecting tool access | (empty) |
If TOKEN is omitted, the service skips authentication. Set it in production environments.
Run the Service
uv run python -m server.anki_server
# or
python -m server.anki_server
FastMCP exposes the tool at http://0.0.0.0:<PORT>/anki and temporary downloads at http://0.0.0.0:<PORT>/downloads.
Usage
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:



License
MIT License
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.