Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者による説明(英語の原文)
Unofficial MCP server for WLED LED controllers; not affiliated with the WLED project
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"wled": {
"command": "uvx",
"args": [
"wled-mcp",
"--transport",
"stdio",
"--config",
"{config_path}",
"--data-dir",
"{data_dir}"
]
}
}
}ターミナルでこれを実行します
claude mcp add wled -- uvx wled-mcp --transport stdio --config '{config_path}' --data-dir '{data_dir}'プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"wled": {
"command": "uvx",
"args": [
"wled-mcp",
"--transport",
"stdio",
"--config",
"{config_path}",
"--data-dir",
"{data_dir}"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"wled": {
"type": "stdio",
"command": "uvx",
"args": [
"wled-mcp",
"--transport",
"stdio",
"--config",
"{config_path}",
"--data-dir",
"{data_dir}"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
この設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月10日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント descipar で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
レジストリには必須のキーは載っていません。ただし、最初に使うときにサインインを求めるサーバーもあります。
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.2.0)がレジストリに届いたのは今日です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにPython (uv)も必要です。
同じカテゴリには:Spec Driven Development, Remote Desktop Commander, Aleksei Shipulin — CV, projects and writing
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:↓ 週あたりのダウンロードi★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Read-only CV, project stories and blog of Aleksei Shipulin, product researcher. EN and RU.
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
An unofficial MCP server that lets an AI agent read and control WLED LED controllers by name: power, brightness, segments, effects, palettes, presets, groups, scenes and zones. It talks to each controller's JSON API on your network, validates every change before sending it and reads it back afterwards. It runs as a subprocess of your MCP host (stdio) or as a separate HTTP service. It is not affiliated with, endorsed by or supported by the WLED project or MCPHub.
Status: early software with 0.x versions that may break between releases (CHANGELOG.md). Releases are distributed on PyPI as wled-mcp (the first two releases are Git tags only); a release that is not listed there installs from its Git tag instead. The server is listed in the official MCP Registry as io.github.descipar/wled-mcp (unofficial, not affiliated with the WLED project); whether a particular MCP host or hub shows that entry was not checked. The container image is not published to GHCR. Hardware acceptance is partial: one controller on WLED 16.0.1. No support is promised (Support).
wled-mcp discover is an opt-in command.effect_name, palette_name) in place of IDs; a name is resolved against that device's catalog before any write and an ambiguous or unknown name is refused with candidates (contract).wled_get_effects parses the firmware's effect metadata and filters by name, 2D and audio reactivity (contract). wled_search_effects finds a device's effects by curated properties such as motion, flashing, colour slots and palette use; the catalog is small and an effect it does not list is not searchable (contract).wled_plan_zone previews the exact segments without a write and wled_apply_zone changes segment fields only inside the zone, otherwise it refuses before any write (contract).change_lighting_safely and precise field descriptions, identically over stdio and HTTP. A client has to pass them on to its agent; forwarding by MCPHub was not observed (contract).read-only, control, full) and, for the HTTP service, a bearer credential with Host and Origin allowlists.All 31 tools, each with its read-only, write or destructive hint, are listed in the tool contract.
WLED feature coverage: 59 % of the planned scope, 47 % of WLED overall (method and list).
You need uv, an MCP host that can start a stdio server and a WLED controller reachable over HTTP; the optional HTTP service also needs Docker with Docker Compose. Replace with the version of the latest release (its tag is v ). The commands install that release from PyPI. If the version is not listed there yet, use the Git route instead: replace wled-mcp== with git+https://github.com/descipar/wled-mcp@v , which builds the package from the tag on your machine; without a tag, uvx takes the current main, which can change at any time. The commands are for a POSIX shell; Windows is experimental (docs/DEVELOPMENT.md).
uvx --isolated --python 3.13 --from wled-mcp==<version> wled-mcp --version
mkdir -p "$HOME/wled-mcp"
uvx --isolated --python 3.13 --from wled-mcp== wled-mcp config init --config "$HOME/wled-mcp/devices.toml" --device-id desk --device-name "Desk strip" --base-url http://
uvx and these arguments, each one separate, using absolute paths: --isolated --python 3.13 --from wled-mcp==<version> wled-mcp --transport stdio --config <absolute path>/wled-mcp/devices.toml --data-dir <absolute path>/wled-mcp
Ask the agent to list your WLED devices (wled_list_devices). Every write tool accepts dry_run=true to preview a change without touching the lights.
Both routes need network access (the Git route to GitHub as well as PyPI). The dependencies are resolved within the ranges the package declares when uvx first creates the tool environment, so they can be newer than the set the release was tested with; for that tested set add the release constraints (dependency policy). For a checksum-verified wheel, more devices, the inventory format and the HTTP service, follow the quickstarts; updates, rollback and removal are in docs/DEPLOYMENT.md.
wled_patch_segments changes only the named segments; only wled_replace_layout removes segments that are not listed.dry_run=true returns the plan without writing. Writes are read back; a write that timed out is reported as possibly applied and is never retried blindly.wled_store_preset) and playlist saves change the live output before they store, and the previous lighting is not restored.overwrite=true is required).What the checks cover; the evidence for each row and the firmware tiers are in docs/contract/compatibility.md. This is not a support commitment (see Support).
| Area | Status |
|---|---|
| Python 3.13 | supported |
| Linux amd64 | supported |
| Linux arm64 | supported |
| HTTP container image, amd64 and arm64 | supported |
| stdio via uvx on Linux | supported |
| Windows | experimental |
| macOS | experimental |
| WLED 16.0.1 | tested |
| WLED 16.x other than 16.0.1 | unknown |
| WLED below 16.0.0, including 0.15.x | unsupported |
Unsupported or unrecognized firmware is served with a warning and never refused; wled_get_state reports the tier in diagnostics.firmware_support.
Automated tests use mocks and synthetic loopback devices. Hardware acceptance covers the first feature set on one RGB controller, and a live check with an offline controller is still pending. A short live check of release 0.1.1 over HTTP and stdio covered state reads, power, brightness and effect changes on that controller (record). A later run on the same controller exercised a one-device group and scene, preset store, export, import and restore, and a playlist, with the controller restored afterwards (record). Multi-device scenes, profiles, discover, restore onto an occupied slot, playlist import, restoring a playlist preset and CCT, RGBW and 2D controllers have no hardware run. Of the newest features, only a read-only run covered the effect metadata and one effect search; zones, name resolution in segment writes and the served guidance have mocked or local-client tests only. Other limits:
wled-mcp config validate and a restart.The complete list and the evidence are in docs/VALIDATION.md.
| Document | Contents |
|---|---|
| Quickstarts | Release directory, stdio and HTTP setup, inventory format |
| Deployment | Both transports in detail: staging, verification, update, rollback, removal |
| Tool contract | Tools, parameters, results, errors and mutation semantics |
| WLED feature coverage | WLED features with support status, owning issue or decision, and coverage figures |
| [Inventory and cl
冒頭だけを表示しています。続きはリポジトリで読めます