nanoodle

Your saved nanoodle workflow graphs as MCP tools — BYOK or pay per call in Nano (x402)

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    No: the server works without sign-in

    Your saved nanoodle workflow graphs as MCP tools — BYOK or pay per call in Nano (x402)

    How to connect

    How to connect nanoodle to Claude

    The server address to paste into Claude settings:

    https://mcp.nanoodle.com/mcp

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect nanoodle to ChatGPT

    The server address to paste into ChatGPT settings:

    https://mcp.nanoodle.com/mcp

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect nanoodle to Cursor

    The server address to paste into Cursor settings:

    https://mcp.nanoodle.com/mcp

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (13)

    Raw names from tools/list. Only developers need these.

    character-spritesDescription → canonical character → separate cutout parts → local rig and animation baking. One text call + two image calls. The companion rig.mjs extracts transparent parts and bakes 32 frames: id… text:Character -> llm:Character designer -> image:Canonical character -> resize:Reference -> edit:Rig parts; returns image + image (muse-image/edit, 1:1) 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. Example: Iron Verdict (https://nanoodle.com/examples/iron-verdict/). A playable fighting game built with character-sprites. This graph generates a character reference and parts sheet; the local skill bakes animated sprites, and a coding agent adds combat, gravity and game rules. Agent skill: https://github.com/nanoodlecom/noodle-skills/tree/main/skills/character-sprites
    combine-imagesUpload a product, then a setting, to preview placement before a photoshoot. Muse Edit uses both reference images ($0.01/image). Inspect product identity, scale and contact shadows; this is a concep… upload:Product photo -> upload:Setting photo -> text:Placement brief -> edit:Product in setting; returns image (muse-image/edit) saved to disk (file path in result). Runs on NanoGPT — $0.18 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed; last run $0.075, ~1m 49s. Example: Reviewed sample (https://nanoodle.com/examples/gallery/#combine-images). A bottle and a mug-on-desk source image combined into one plausible scene. The sample includes both inputs; exact product fidelity needs a separate comparison.
    deslopEdit a customer notice without losing prices, dates or caveats. Grok drafts; a second model compares the draft with the source; Grok applies the review. Three paid text calls. The review checks wri… text:Your draft -> llm:First rewrite -> join:Source and rewrite -> llm:Fact and clarity review -> join:Source, rewrite and review -> llm:Edited notice; returns text. Runs on NanoGPT — $0.10 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed; last run $0.0341, ~78s. Example: Reviewed sample (https://nanoodle.com/examples/gallery/#deslop). A repair-booking announcement rewritten in plain language while retaining the supplied facts. Compare the source and result in the sample; this is an editorial workflow, not an authorship detector.
    edit-a-photoUpload a product photo and make a clean catalog image. Muse Edit preserves the product while changing the background ($0.01/image). Check logos, small details and color against the original before … upload:Product photo -> text:Edit request -> edit:Clean product photo; returns image (muse-image/edit) saved to disk (file path in result). Runs on NanoGPT — $0.18 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed; last run $0.075, ~80s. Example: Reviewed sample (https://nanoodle.com/examples/gallery/#edit-a-photo). A bottle image edit with its source and instruction documented in the sample. The shape remains recognizable; compare any markings that must survive an edit of your own product.
    faviconTurn a brand brief into a square favicon concept. GLM Flash condenses the brief; Muse renders one image (image step $0.01, plus text). Inspect at 16px; export or convert to favicon sizes separately. text:Brand -> llm:Icon prompt -> image:Favicon; returns image (muse-image/text-to-image, 1:1) saved to disk (file path in result). Runs on NanoGPT — $0.03 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed; last run $0.0101, ~43s. Example: Reviewed sample (https://nanoodle.com/examples/gallery/#favicon). A lighthouse-inspired icon for a pocket weather radio. The output is a raster concept; creating an ICO or SVG requires a separate step.
    fibo-studio-stillCreate an editorial product concept from a description and lighting choice. GLM Flash structures the brief; Bria FIBO renders at 1MP (image step $0.04, plus text). FIBO is offered as a model traine… text:Product -> choice:Light -> join:Brief -> llm:Structured prompt -> image:Still; returns image (fibo-generate-1.5/text-to-image, 1mp) saved to disk (file path in result). Runs on NanoGPT — $0.10 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed. Example: Reviewed sample (https://nanoodle.com/examples/gallery/#fibo-studio-still). An amber soap bottle rendered from a product brief and lighting choice. This is a generated concept, not a photograph of an existing product.
    image-model-arenaCompare four image models on the same useful brief. Run makes four paid images. Judge exact text, object count, composition and color before choosing the model for your own task. Each contender alr… text:Shared test brief -> image:Contender 1 -> image:Contender 2 -> image:Contender 3 -> image:Contender 4; returns image (muse-image/text-to-image, 1:1) + image (turbo, 1k) + image (grok-imagine-image/v2.0/text-to-image, 1:1) + image (recraft-v4, 1024×1024) saved to disk (file paths in result). Runs on NanoGPT — $0.59 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed; last run $0.2455, ~1m 39s. Example: Reviewed sample (https://nanoodle.com/examples/gallery/#image-model-arena). The same bicycle-repair poster brief sent to four image models. All four retained the requested text in this run; only Grok rendered recognizable tire levers. Compare all outputs before choosing.
    night-market-postcardCreate a landscape travel postcard illustration from a place and mood. Change both inputs for a new destination. GLM Flash writes the prompt; Muse renders at 3:2 (image step $0.01, plus text). Insp… text:Place -> choice:Vibe -> join:Spec -> llm:Postcard prompt -> image:Postcard; returns image (muse-image/text-to-image, 3:2) saved to disk (file path in result). Runs on NanoGPT — $0.03 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed. Example: Reviewed sample (https://nanoodle.com/examples/gallery/#night-market-postcard). An illustrated Raohe night-market postcard from the saved place and atmosphere inputs. Use it as creative artwork rather than a documentary record.
    omni-flash-turntableCreate a short product-motion concept from an object and camera move. GLM Flash structures the brief; Omni Flash 1.1 renders 5s at 360p / 16:9 (video step $0.195, plus text). No upload required. In… text:Object -> choice:Move -> join:Brief -> llm:Video prompt -> tvideo:Clip; returns video (gemini-omni-flash/v1.1) saved to disk (file path in result). Runs on NanoGPT — $0.10 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed. Example: Reviewed sample (https://nanoodle.com/examples/gallery/#omni-flash-turntable). A 360p draft camera orbit around a generated bottle with coherent geometry in the reviewed clip. This thumbnail is one frame; open the sample to inspect the motion.
    photo-to-videoMake a five-second ambient loop concept: Muse draws the first frame ($0.01), MiniMax H3 Spicy animates one small movement (480p, $0.20). This model supports image-to-video; the scene is a simple pr… text:Still brief -> text:Motion brief -> image:First frame -> ivideo:Animated clip; returns video (image-to-video-spicy) saved to disk (file path in result). Runs on NanoGPT — $0.51 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed. Example: Reviewed sample (https://nanoodle.com/examples/gallery/#photo-to-video). A short tea-on-a-desk animation. Sampled frames retained the mug while steam moved. This thumbnail is one frame; the example does not establish a seamless loop.
    render-a-mockupTurn a screen brief and visual style into a UI concept for design review. Qwen Image 3 Pro renders at 1K ($0.04/image); no prompt-writing call. Keep the combined brief and style under the model lim… text:Screen brief -> text:Visual style -> join -> image:Screen concept; returns image (qwen-image-3-pro, 1k) saved to disk (file path in result). Runs on NanoGPT — $0.20 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed; last run $0.079, ~2m 16s. Example: Reviewed sample (https://nanoodle.com/examples/gallery/#render-a-mockup). A repair-shop dashboard concept with the requested navigation, date, three appointment rows, names, statuses and totals. This is a rendered screen concept; implementation and interaction are separate work.
    singDraft an original closing-credits song. One text model writes lyrics; Mureka Generate Song sings them using the editable musical style. Music step $0.225, plus text. Listen for clear words, melody … text:Song Instructions -> text:Musical style -> llm:Lyrics -> music:Song; returns audio (mureka-v9.5/generate-song) saved to disk (file path in result). Runs on NanoGPT — $0.55 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed; last run $0.0497, ~1m 56s. Example: Audio sample (https://nanoodle.com/examples/gallery/#sing). A 170-second generated closing-credits song. Gemini 3.8 Flash reported clear gentle acoustic vocals and a chorus matching the supplied lyrics. This is model-assisted audio review, not human listening sign-off.
    talking-avatarPrototype a short spoken introduction with a fictional presenter. Muse makes the portrait, MiniMax Speech reads the script, and LongCat animates speech at 480p. Keep scripts under 30 seconds. Cost … text:Presenter look -> text:Spoken script -> text:Delivery -> image:face -> tts -> lipsync; returns video (longcat-avatar-1.5) saved to disk (file path in result). Runs on NanoGPT — $0.63 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed. Example: Video sample (https://nanoodle.com/examples/gallery/#talking-avatar). A fictional presenter reads a short workshop introduction. Sampled frames preserve the presenter; check precise lip-sync timing in playback. Generation can take several minutes.