広告掲載
MCP.so
ログイン

MCP Divoom TimeFrame Lan

@DivoomDevelop

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

DivoomDevelop

投稿者

DIVOOM

MCP Divoom TimeFrame Lan について

mcp-divoom-lan is an open-source Model Context Protocol (MCP) server that exposes Divoom watchface customization over local LAN HTTP. AI assistants can read and patch the current on-device watchface JSON, manage fonts and store market lists, switch the active dial, adjust brightn

#mcp#divoom#watchface#lan#iot#smart-device#node-js#stdio#home-automation#timeframe#timegate#pixoo64

MCP Divoom TimeFrame Lan の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "divoom-lan": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-divoom-lan"
      ],
      "env": {
        "DIVOOM_DEVICE_HOST": "192.168.1.120",
        "DIVOOM_DEVICE_PORT": "9000",
        "DIVOOM_TIMEOUT_MS": "45000"
      }
    }
  }
}

MCP Divoom TimeFrame Lan のツール

18

Call Device/GetLocalClockInfo for current or explicit clock id.

Patch local dial via Device/PatchLocalClockInfo with precheck. Defaults to POST /divoom_api (JSON only) for pure metadata edits. Prefer ItemPatchList (per-index field diff) — DO NOT include item_id inside patch.* unless the user explicitly asks to rename a slot, since the firmware will overwrite the device-side item_id and break menu/config bindings. When dialAssetsPath is set, switches to multipart POST /patch_local_clock: first JSON part (Device/PatchLocalClockInfo, optional DialAssets), second part single JPEG/WebP dial backdrop or clock_bg.tar.gz bundle. Element slots inside the tarball must be JPEG, WebP, or PNG (validated by firmware wf_validate_bundle_slot_image_file). Use ItemPatchList[].patch.bundle_image=<leaf> to bind a tar leaf to that slot's img_addr; supplying ItemList alone is a full-table replace and should be avoided unless the row count actually changes. Multipart framing (Content-Length / boundary / manual construction): see watchface_upload_file description and resources/skill-quick-reference.md.

Call Device/GetLocalFontList.

Call Device/GetStoreClockMarketList after device prefetch has populated in-memory store data.

Call Channel/SetClockSelectId with ClockId.

Call Sys/GetBrightness.

Call Channel/SetBrightness with Brightness.

Call Channel/OnOffScreen with OnOff (1=on, 0=off).

POST /replace_clock_dial_bg using multipart (Device/ReplaceClockDialBgFile). Replaces the cached dial bitmap only — does NOT modify cfg DeviceImageUrl, and does NOT accept tar.gz. Backdrop is validated by divoom_watchface_replace_clock_dial_bg_validate_saved_file: JPEG (FF D8) or WebP (RIFF…WEBP) only, ≤ 500 KiB (DIVOOM_REPLACE_DIAL_BG_MAX_FILE_BYTES), recommended 800x1280 portrait. Multipart framing notes: watchface_upload_file description.

POST /upload with multipart. First JSON part is caller-provided metadata (product-specific Command). 传输文件打包要求：固件在 divoom_http_server_upload_get_file_info 中要求每个文件段必须有 Content-Length，而浏览器 FormData 通常只使用 boundary 分隔、不包含每段 Content-Length。正在实现固件在无 Content-Length 时用 boundary 终止解析，并修复 JSON 段之后定位文件数据的指针计算；编辑器侧改为手动构造带 Content-Length 的 multipart 以提高兼容性。This server builds multipart with per-part Content-Length.

POST /create_local_clock (multipart) — Device/CreateLocalClock. metadata.DialAssets accepts 'auto' (default; sniffs gzip magic on the file part), 'image' (single JPEG/WebP backdrop), or 'bundle' (clock_bg.tar.gz). Legacy UseDialAssetBundle (0=image, non-0=bundle) is honored when DialAssets is omitted. Backdrop is JPEG/WebP only; element slots inside the tarball accept JPEG/WebP/PNG (firmware wf_validate_bundle_slot_image_file). Each ItemList[i] needs disp/font/x/y/w/h/size/alig numbers and color_1/color_2/item_id non-empty strings; ItemIdList must be a parallel non-empty string array. alig: 3=center, 4=left, 5=right. Multipart framing (Content-Length per part): see watchface_upload_file description.

Call Device/ResetLocalClockFromServer. This deletes local sys-side files before optional cloud refresh.

Raw POST /divoom_api command wrapper. Command is required; payload object is merged with enforced ReturnCode=0.

Return concise operational constraints extracted from the public guide and skill.

Return the full `disp` id catalog (194 entries) that the firmware understands for `ItemList[i].disp` and `ItemPatchList[i].patch.disp`. Each entry includes English symbol, Chinese description, and heuristic hints (`likelyUsesRasterOrAssetLayer` for image/GIF slots; `oftenUsesVectorFontForText` for text slots). Use it together with `watchface_font_catalog`: text-leaning disps need a font id; raster-leaning disps need an `image_addr` asset.

Return a curated font catalog so agents can pick `ItemList[i].font` ids deterministically. Each entry includes id, type (1=TTF, 0=image-font), display name, original charset, derived script (digits / digits-extended / latin / cjk), style tags (sans/serif/pixel/digital/handwriting/display/decorative/bold/light/etc), and recommendedFor (scenario names like time_digits / temperature_digits / weather_text / user_text / lunar_text). The response also includes a `scenarios` map that lists which `disp` ids each scenario covers and which tags to prefer. Use the optional filters to narrow the result. Always cross-check with `watchface_get_fonts_local` before committing a font id to a real device, because the on-device font list may be a subset.

Search the curated template library (`divoom://templates/curated`): ~20 marketplace-derived watchface skeletons with tags such as weather, lunar_calendar, split_time_digits, pixel_theme, asset_heavy. Prefer cloning an existing ItemList layout before inventing raw coordinates. Filters support tagsAll/tagsAny, bucket, clockIds, item-count bounds, and dispPresent (template must include that disp id). Set includeWatchface=false for a compact summary without the full ItemList payload.

Return layout hints for a single disp id by combining disp-catalog metadata with aggregated typography (median size/x/y/w/h, frequent colors, alignment mode) mined from bundled marketplace templates. Use before authoring a new ItemList row or ItemPatchList.patch fragment — values are soft guidance, not firmware-enforced. Always clamp boxes to the logical canvas (typically 800×1280).

概要

What is Mcp Divoom TimeFrame Lan?

Mcp Divoom TimeFrame Lan is an open-source Model Context Protocol (MCP) server for Divoom watchface customization over local LAN HTTP. It enables users to drive on-device watchface workflows in natural language from Cursor, Claude Desktop, or any MCP-compatible client.

How to use Mcp Divoom TimeFrame Lan?

Requires Node.js 20+ and network access to the Divoom device on the same LAN (HTTP API, commonly port 9000). Configure by setting environment variables: DIVOOM_DEVICE_HOST (device IP), DIVOOM_DEVICE_PORT (default 9000), and DIVOOM_TIMEOUT_MS (default 45000). Invoke tool calls from any MCP client; the target parameter can also be passed per call.

Key features of Mcp Divoom TimeFrame Lan

  • Read and patch the current local watchface
  • List local fonts and store/market dials
  • Switch active dial and read/set brightness
  • Multipart helpers for dial background replacement and file upload
  • Exposes MCP resources with protocol and safety notes for agents

Use cases of Mcp Divoom TimeFrame Lan

  • Customizing Divoom watchfaces on-device using natural language from an MCP client
  • Switching between active dials programmatically over local LAN
  • Reading or adjusting device brightness without a proprietary app

よくある質問

1

What does Mcp Divoom TimeFrame Lan do?

It is an MCP server that allows reading, patching, and managing Divoom watchfaces over local LAN HTTP from MCP-compatible clients.

2

What are the runtime requirements?

Node.js 20+ and network access to the Divoom device on the same LAN, typically using port 9000.

3

How do I configure the server?

Set environment variables: `DIVOOM_DEVICE_HOST` for the device IP, `DIVOOM_DEVICE_PORT` (default `9000`) for the HTTP port, and `DIVOOM_TIMEOUT_MS` (default `45000`) for timeout.

4

What safety precautions are recommended?

Prefer a read → patch → read back workflow before trusting changes. Some operations, such as reset from cloud, can be destructive; confirm with the user first.

5

Where can I find the source and report issues?

The repository is at https://github.com/DivoomDevelop/mcp-divoom-lan. Security issues can be reported to developer@divoom.com, and npm package is `mcp-divoom-lan`.

コメント

「その他」の他のコンテンツ

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K
P

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Lemon.io

lemon-io

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3

Health by Dr Brad

Dr Brad Stanfield

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one

Senso MCP for Joomla

sensomedia

Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea

広告掲載