For those who wish to run the mcp as a docker , here's a working solution:
Download the repo and within that folder create a file named "Dockerfile":
FROM ghcr.io/astral-sh/uv:python3.13-bookworm-slim
WORKDIR /app
ENV UV_PYTHON=python3.13
ENV UV_PYTHON_PREFERENCE=only-managed
COPY . .
RUN uv sync --link-mode=copy && \
cp "hotfixes/emby/configuration.py" ".venv/lib/python3.13/site-packages/emby_client/" && \
cp "hotfixes/emby/user_service_api.py" ".venv/lib/python3.13/site-packages/emby_client/api/"
EXPOSE 12345
CMD ["uv", "run", "python", "emby_mcp_server.py", "run", "--transport", "sse", "--host", "0.0.0.0", "--port", "12345"]
and also create a file named ".env":
EMBY_SERVER_URL="http://host.docker.internal:8096" EMBY_USERNAME="your-emby-username" EMBY_PASSWORD="your-emby-password" EMBY_VERIFY_SSL=False LLM_MAX_ITEMS=100
run the command docker build -t emby-mcp-agent .
and then fire it up with docker run -d -p 12345:12345 -v "%cd%\.env:/app/.env" --name emby-mcp emby-mcp-agent
For those who wish to run the mcp as a docker , here's a working solution:
Download the repo and within that folder create a file named "Dockerfile":
and also create a file named ".env":
EMBY_SERVER_URL="http://host.docker.internal:8096" EMBY_USERNAME="your-emby-username" EMBY_PASSWORD="your-emby-password" EMBY_VERIFY_SSL=False LLM_MAX_ITEMS=100run the command
docker build -t emby-mcp-agent .and then fire it up with
docker run -d -p 12345:12345 -v "%cd%\.env:/app/.env" --name emby-mcp emby-mcp-agent