MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
作者提供的说明(英文原文)
Official LabelGrid MCP server — manage your music catalog, releases, analytics and distribution.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
LABELGRID_API_TOKEN, LABELGRID_API_URL, LABELGRID_ENABLE_WRITES, LABELGRID_ENABLE_FULL_WRITES, LABELGRID_FULL_WRITES_ACK, LABELGRID_TOOLSETS, LABELGRID_READ_ONLY标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"labelgrid": {
"command": "npx",
"args": [
"-y",
"@labelgrid/mcp"
],
"env": {
"LABELGRID_API_TOKEN": "your-value",
"LABELGRID_API_URL": "your-value",
"LABELGRID_ENABLE_WRITES": "your-value",
"LABELGRID_ENABLE_FULL_WRITES": "your-value",
"LABELGRID_FULL_WRITES_ACK": "your-value",
"LABELGRID_TOOLSETS": "your-value",
"LABELGRID_READ_ONLY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add labelgrid --env LABELGRID_API_TOKEN=your-value --env LABELGRID_API_URL=your-value --env LABELGRID_ENABLE_WRITES=your-value --env LABELGRID_ENABLE_FULL_WRITES=your-value --env LABELGRID_FULL_WRITES_ACK=your-value --env LABELGRID_TOOLSETS=your-value --env LABELGRID_READ_ONLY=your-value -- npx -y @labelgrid/mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"labelgrid": {
"command": "npx",
"args": [
"-y",
"@labelgrid/mcp"
],
"env": {
"LABELGRID_API_TOKEN": "your-value",
"LABELGRID_API_URL": "your-value",
"LABELGRID_ENABLE_WRITES": "your-value",
"LABELGRID_ENABLE_FULL_WRITES": "your-value",
"LABELGRID_FULL_WRITES_ACK": "your-value",
"LABELGRID_TOOLSETS": "your-value",
"LABELGRID_READ_ONLY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"labelgrid": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@labelgrid/mcp"
],
"env": {
"LABELGRID_API_TOKEN": "your-value",
"LABELGRID_API_URL": "your-value",
"LABELGRID_ENABLE_WRITES": "your-value",
"LABELGRID_ENABLE_FULL_WRITES": "your-value",
"LABELGRID_FULL_WRITES_ACK": "your-value",
"LABELGRID_TOOLSETS": "your-value",
"LABELGRID_READ_ONLY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
LABELGRID_API_URL envLABELGRID_ENABLE_WRITES envLABELGRID_ENABLE_FULL_WRITES envLABELGRID_FULL_WRITES_ACK envLABELGRID_TOOLSETS envLABELGRID_READ_ONLY env这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
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6日
注册名称已通过 GitHub 账户 labelgrid 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
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
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 1 项适用的基础检查中通过了 1 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。
你需要填写:LABELGRID_API_TOKEN
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–,最新版本(0.4.0)于3个月前进入注册中心。
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 Node.js。
同一分类中有:MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ 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
An MCP server retrieving transcripts of YouTube videos
GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
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。
The official LabelGrid tooling for the LabelGrid public API, organised as an npm workspace.
Looking for the MCP server docs? They live in packages/mcp/README.md — installation for Claude Desktop / Cursor / any MCP client, the full tool reference, safety gating, and configuration.
| Package | What it is |
|---|---|
@labelgrid/mcp | The MCP server — 30 consolidated tools over the LabelGrid public API. Published to npm; also ships as the labelgrid.mcpb one-click bundle for Claude Desktop. |
@labelgrid/cli | The labelgrid command-line tool — the same API surface for terminals and scripts: catalog, releases, files, analytics, royalties, webhooks, and distribution, with --json output for pipelines. |
@labelgrid/core | The shared API client: HTTP transport with structured errors, presigned-URL uploads, content-type allowlists, the catalog-entity registry, and redacting logging. Used by every LabelGrid tool built on the public API. |
Full docs (auth setup, every command group, scripting, safety model) live in packages/cli/README.md. Quickstart:
npm install -g @labelgrid/cli # Node 20+; installs the `labelgrid` command
export LABELGRID_API_TOKEN=... # or run labelgrid auth login labelgrid auth whoami # verify the token labelgrid catalog search --type release --json | jq '.data[].id'
skills/labelgrid-release/SKILL.md is an agent skill for the full release lifecycle — draft a release and its tracks, upload audio and artwork, validate, review, distribute, and track delivery — with the exact MCP tool and CLI command for each step and guidance on which vehicle fits. Point an agent at the file, or drop it into your assistant's skills directory, to teach it the end-to-end LabelGrid release flow.
package.json is a private workspaces manifest; its scripts fan out to the packages (npm run build builds @labelgrid/core first, then @labelgrid/mcp and @labelgrid/cli; npm test runs each package's suite). Contributors work from the repo root: packages/core is the shared client, packages/mcp the MCP server, packages/cli the command-line tool — the two products are thin adapters over core.tsconfig.base.json (no TypeScript project references — the explicit root build chain keeps ordering correct and simple). @labelgrid/mcp imports @labelgrid/core through the workspace link and compiles against its built declarations.vitest.config.ts. The MCP package aliases @labelgrid/core to the sibling package's TypeScript source, so running tests never requires a prior core build.scripts/ and run from the root: npm run lint, npm run leak-guard, npm run check-coverage, npm run gen-docs, npm run measure-tokens.npm ci # install the whole workspace
npm run build # build core, then mcp and cli npm test # unit suites for every package npm run lint # biome over the repo
The MCP server binary after a build: node packages/mcp/dist/index.js (or npm start). The CLI binary after a build: node packages/cli/dist/index.js.
MIT