starcoder server for huggingface-vscdoe custom endpoint.
Can't handle distributed inference very well yet.
Fill http://localhost:8000/api/generate/ into Hugging Face Code > Model ID or Endpoint in VSCode.
curl -X POST http://localhost:8000/api/generate/ -d '{"inputs": "", "parameters": {"max_new_tokens": ""}}'
# response = {"generated_text": ""}
$ claude mcp add huggingface-vscode-endpoint-server \
-- python -m otcore.mcp_server <graph>