nanoodle-mcp v0.4.0

Connect from Claude Code

claude mcp add --transport http noodles https://mcp.nanoodle.com/mcp

Then just ask for what you want. When a tool needs payment, your agent shows you a link with a QR code — scan it with any Nano wallet and the result streams back seconds later. Failed runs are refunded automatically.

Tools (11)

• auto-dub-noodle-graph
  Extracts audio, transcribes, translates, re-speaks — then lays the new voice back over the clip. vupload -> extractaudio -> transcribe -> llm -> tts -> soundtrack; returns video saved to disk (file path in result). Runs on NanoGPT — $0.05 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed.
• edit-a-photo-noodle-graph
  Repaints an uploaded photo according to an edit described in plain words. upload -> edit; returns image saved to disk (file path in result). Runs on NanoGPT — $0.05 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed.
• extend-a-video-noodle-graph
  Grabs the last frame of your clip and hands it to image→video — the shot keeps going. vupload -> vframes -> ivideo; returns video (p-video/image-to-video) saved to disk (file path in result). Runs on NanoGPT — $0.05 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed.
• lyrics-to-song-noodle-graph
  One idea fans out to two LLMs — lyrics plus a matching style — then a music model sings it. text -> llm×2 -> music; returns audio (Minimax-Music-02) saved to disk (file path in result). Runs on NanoGPT — $0.05 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed.
• model-arena-noodle-graph
  Pick a DIFFERENT model on each Contender, then Run — same prompt four ways, side by side. text -> image:Contender 1 -> image:Contender 2 -> image:Contender 3 -> image:Contender 4; returns image (gpt-image-1.5) + image (v4/instant) + image (hidream-o1-image) + image (v2/medium/text-to-image) saved to disk (file paths in result). Runs on NanoGPT — $0.05 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed.
• photo-to-video-noodle-graph
  Generates a still image from a prompt, then animates it into a short video clip. text -> image -> ivideo; returns video (p-video/image-to-video) saved to disk (file path in result). Runs on NanoGPT — $0.05 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed.
• see-think-speak-noodle-graph
  A vision model describes your photo, an LLM distills it into a poem, and speech reads it aloud. upload -> vision -> llm -> tts; returns audio (Kokoro-82m) saved to disk (file path in result). Runs on NanoGPT — $0.05 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed.
• style-switchboard-noodle-graph
  Flip the Choice switch and re-run — same scene, five art styles. text -> choice -> join -> image; returns image (nano-banana-2-lite) saved to disk (file path in result). Runs on NanoGPT — $0.05 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed.
• talking-avatar-noodle-graph
  TTS speaks your line, and the lipsync model animates the portrait to match. upload -> text -> tts -> lipsync; returns video (latentsync) saved to disk (file path in result). Runs on NanoGPT — $0.05 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed.
• text-to-image-noodle-graph
  The one-wire hello-world of noodling — describe a scene, get an image. text -> image; returns image (nano-banana-2-lite) saved to disk (file path in result). Runs on NanoGPT — $0.05 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed; last run $0.04, ~17s.
• voice-memo-to-notes-noodle-graph
  Transcribes a rambling voice memo, then an LLM tidies it into a summary, bullets, and action items. aupload -> transcribe -> llm; returns text. Runs on NanoGPT — $0.05 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed.