impeccable
The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.
Model Context Protocol (MCP) server for Luminous Music Player
作者提供的原文
教 AI 做这类工作的 Skill,可与本项一起使用
The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.
Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, Qoder, and Pi. 45 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.
Create beautiful slides on the web using a coding agent's frontend skills
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 0/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 0/8 | 上次检查时云端端点有响应 |
| 使用分 | 12/100 |
质量: 基础检查通过 2/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
选择你使用的 AI 应用,然后复制设置。
通过 2/3 项检查 · 在你的电脑上运行
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
用 Luminous Music Player 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Luminous Music Player,或回答中出现 Luminous Music Player 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 Luminous Music Player
Luminous Music Player 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
A · 使用能连接 Luminous Music Player 的应用
B · 设计、图片与音频 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的
Claude Code 暂时无法连接 Luminous Music Player
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Luminous Music Player 的应用
Cursor 暂时无法连接 Luminous Music Player
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Luminous Music Player 的应用
VS Code 暂时无法连接 Luminous Music Player
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Luminous Music Player 的应用
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日
注册名称已通过 GitHub 账户 esoltys 验证,该账户拥有此仓库
代码最后更新于5天前
仓库中没有找到许可证文件
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/esoltys-luminous-mcp)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 3 项适用的基础检查中通过了 2 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于5天前,最新版本(1.13.0)于5天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 MCPB。
同一分类中有:HyperFrames by HeyGen, Pascal 3D Editor, draw.io, Figma MCP Server, Remocn: Remotion MCP server
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Official HyperFrames by HeyGen: the best AI video editor in chat. Captions, motion graphics, MP4.
Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.
Create draw.io diagrams in chat from Mermaid or XML, shown live and interactive. 10,000+ shapes.
The Figma MCP server brings Figma design context directly into your AI workflow.
Hosted MCP for Remotion videos: search Remocn components, read docs, plan a video, preview it.
| 本项 Luminous Music Player | HyperFrames by HeyGen | Pascal 3D Editor | draw.io | Figma MCP Server | Remocn: Remotion MCP server | |
|---|---|---|---|---|---|---|
| 运行位置 | 需要安装在电脑上 | 在云端运行,无需安装 | 云端或安装在电脑上都可以 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 是 | 否 | 否 | 是 | 否 |
| 基础检查 | 2/3 | 4/4 | 5/5 | 4/4 | 4/4 | 4/4 |
| 许可证 | – | Apache-2.0 | MIT | Apache-2.0 | – | MIT |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
A Model Context Protocol (MCP) server for Luminous Music Player.
Connects your AI assistants (Claude Desktop, Antigravity, Cursor, Zed, Ollama) to your local music library.
Here are prompt examples demonstrating natural language queries you can ask your AI assistant:
Luminous MCP implements strict token-efficiency and context window optimization best practices designed specifically for LLMs:
| Optimization Feature | Implementation | Token & Context Window Impact |
|---|---|---|
| Compact JSON Serialization | Stripped indentation whitespace by default (JSON.stringify(obj)); optional pretty printing via pretty argument or LUMINOUS_PRETTY_JSON=1 | 15%–25% reduction across all tool responses |
| Sparse Field Pruning | Recursively strips null, undefined, and empty strings ("") while preserving semantic falsy values (0, false, []) | 25%–35% reduction across metadata-dense inspection tools |
| On-Demand Lyrics Gating | Full song lyrics gated behind explicit include_lyrics: true flag in get_track_details (defaults to boolean indicator has_lyrics) | 500–1,500+ tokens saved per track lookup |
| Search Detail Levels | search_library defaults to compact essential fields (id, title, artist, album, year, duration_seconds); detail_level: "full" on demand | 50%–70% reduction on search listings |
| Metric Deduplication | Canonical ISO 8601 timestamps (last_played_iso, played_at_iso), single float ratios (skip_ratio), and seconds durations (duration_seconds) | 15%–20% reduction on analytics and history queries |
| Bounded Collections | Caps artist summary entity lists (collaborators, composers, producers) to top 20 frequency-ranked entries, while returning total counts | Prevents 1,000–3,000+ token explosions on prolific artists |
| Offset Pagination | Incremental limit & offset pagination with total_matches and has_more metadata for search_library, get_recent_history, find_artists_by_tag and list_artists (full-library artist enumeration with has_profile curation flag and country filter) | Eliminates redundant page re-fetching during multi-turn exploration |
git clone https://github.com/esoltys/luminous-mcp.git
cd luminous-mcp bun install bun run build
bun run start
In portable mode (a portable or luminous.portable file, or a data/ folder, next to the Luminous executable) the library lives in /data/luminous.db, which the server cannot discover automatically. Point it there with LUMINOUS_DATA_DIR= /data (or LUMINOUS_DB_PATH).
update_artist_profile / update_artist_profiles only accept curated attribute tags: by default nationality (Canadian) and named awards (Grammy Award) are allowed, genre and decade/era tags are rejected, and other tags are accepted with a warning. get_tag_policy returns the rules in force and list_artist_tags reports every tag in use (case variants grouped, each marked allowed / unknown / denied) without changing anything.
To use your own rules, point LUMINOUS_ARTIST_TAG_VOCAB at a JSON file. It replaces the defaults entirely and a missing or invalid file stops the server at startup:
{
"unknown_tags": "reject", "categories": [ { "id": "label", "label": "record label", "kind": "allowed", "description": "Label", "values": ["Sub Pop"], "examples": ["Sub Pop"] }, { "id": "mood", "label": "mood", "kind": "denied", "description": "Moods are subjective", "values": ["Sad"] } ] }
values match tags exactly and patterns are regular expressions matched against the whole tag, both case-insensitively. Denied categories win over allowed ones. Decade/era tags are still rejected on album profiles when the vocabulary has a category with id decade_era.
.mcpb)Install directly via the official MCP Bundle (.mcpb) format (zero external dependencies; includes a self-contained binary):
.mcpb for your OS/architecture from GitHub Releases (or build locally with bun run package:mcpb to produce dist/luminous-mcp.mcpb)..mcpb file into Settings > Extensions).Note: Anthropic deprecated standalone
.mcpbdesktop extension listings inclaude.ai/directory, and public directory submissions for local (stdio) MCP servers are currently restricted to Verified organizations usingnode/python/bashlaunchers (whereasluminous-mcpusesbun:sqlite). Use the signed.mcpbreleases above for Claude Desktop, or the Plugin Bundle below for direct Claude Code installs.
This repository includes .claude-plugin/plugin.json, .mcp.json, and skills/luminous/SKILL.md for direct installation as a local Claude Code plugin from GitHub (requires Bun v1.1+ on PATH).
Alternatively, add luminous to your claude_desktop_config.json or MCP client configuration:
{
"mcpServers": { "luminous": { "command": "bun", "args": ["run", "C:/path/to/luminous-mcp/src/index.ts"] } } }
When running AI assistants or agents inside a container, WSL sandbox, or remote host, run Luminous MCP natively on the host with the SSE HTTP transport:
bun run start:sse
By default, this listens on http://0.0.0.0:21850/sse (override with LUMINOUS_MCP_PORT and LUMINOUS_MCP_HOST). It also exposes a GET /health endpoint for health checks.
Connect your client using the SSE URL:
{
"mcpServers": { "luminous": { "url": "http:// :21850/sse" } } }
For OpenClaw running in WSL or Docker:
openclaw mcp add luminous --url http://<host-ip>:21850/sse --transport sse
Each .mcpb bundle is signed with an embedded PEM signature (mcpb sign), and each release publishes SHA256SUMS.txt plus SHA256SUMS.txt.sigstore.json, a cosign keyless signature made by this repository's Release workflow (no certificate is bought or stored; the signing identity is recorded in the public Sigstore log). To verify a download:
bun x @anthropic-ai/mcpb verify luminous-mcp-linux-x64.mcpb
bun x @anthropic-ai/mcpb info luminous-mcp-linux-x64.mcpb
And to verify the release checksums with Cosign:
cosign verify-blob SHA256SUMS.txt \
--bundle SHA256SUMS.txt.sigstore.json \ --certificate-identity-regexp '^https://github.com/esoltys/luminous-mcp/\.github/workflows/release\.yml@refs/tags/v.*$' \ --certificate-oidc-issuer https://token.actions.githubusercontent.com sha256sum --check --ignore-missing SHA256SUMS.txt # macOS: shasum -a 256 -c
The .mcpb signature verifies the bundle archive itself; the standalone binaries inside are not OS code-signed, so Windows SmartScreen or macOS Gatekeeper may warn on first run.
Bump version in package.json, SERVER_VERSION in src/constants.ts, and