MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
作者提供的说明(英文原文)
Pre-computed metadata context engine for AI-driven data analytics
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。
ANTHROPIC_API_KEY, DATARAUM_HOME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": {
"dataraum": {
"command": "uvx",
"args": [
"dataraum"
],
"env": {
"ANTHROPIC_API_KEY": "your-value",
"DATARAUM_HOME": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add dataraum --env ANTHROPIC_API_KEY=your-value --env DATARAUM_HOME=your-value -- uvx dataraum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": {
"dataraum": {
"command": "uvx",
"args": [
"dataraum"
],
"env": {
"ANTHROPIC_API_KEY": "your-value",
"DATARAUM_HOME": "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": {
"dataraum": {
"type": "stdio",
"command": "uvx",
"args": [
"dataraum"
],
"env": {
"ANTHROPIC_API_KEY": "your-value",
"DATARAUM_HOME": "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。
DATARAUM_HOME 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 dataraum 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:ANTHROPIC_API_KEY
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(0.2.1)于7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 Python (uv)。
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 understanding layer that grounds an organization's operating model in its own data.
A semantic layer tells BI tools what columns are *called*. DataRaum learns what they *mean* — the concepts, relationships, rules, and measures of the organization — and grounds each one in the actual data, with a measured confidence behind it. See the docs for the full picture.
packages/
├── engine/ # Python — pipeline, detectors, Temporal activity worker ├── cockpit/ # TypeScript — TanStack Start web UI ├── dataraum-config/ # YAML data — entropy config, LLM prompts, verticals (bind-mounted, never imported) └── infra/ # docker-compose orchestration
Each package has its own README. Start there if you're working in a specific package.
DataRaum runs as a multi-container platform, isolated per workspace:
add_source, begin_session, operating_model) and writes metadata to the workspace's Postgres schema.Each workspace runs its own pair of those two containers. In front of them sit the portal (the cockpit image in a second role — login, membership routing, workspace provisioning) and Caddy, which serves the portal on the parent domain and each workspace on its own subdomain.
They share one substrate: Postgres (metadata + cockpit state + catalogs), an S3 object store (the DuckLake data lake + uploads), and Temporal (durable orchestration). No HTTP seam between engine and cockpit — the integration surface is Postgres + Temporal. See the platform architecture.
# Set the LLM key
cp packages/infra/.env.example packages/infra/.env echo "ANTHROPIC_API_KEY=sk-ant-..." >> packages/infra/.env
docker compose -f packages/infra/docker-compose.yml up -d --wait
docker compose -f packages/infra/docker-compose.yml run --rm --no-deps \ --entrypoint temporal temporal-admin-tools \ worker list --namespace default --address temporal:7233 # → Status: Running
open http://dataraum.localhost # dev@dataraum.dev / dataraum-dev
Caddy routes by hostname: the parent domain serves the portal (login + your workspaces), and each workspace has its own subdomain (http://ws1.dataraum.localhost). localhost:3000 is published for debugging only — the session cookie is scoped to the parent domain, so a browser there is redirected to the portal and a script gets 401.
The thing that bites on a first run: Caddy binds port 80. If something already holds it (macOS ships Apache), up fails at container start and the portal never comes up — set CADDY_HTTP_PORT *and* a matching DATARAUM_PORTAL_ORIGIN to move it. (*.localhost needs no /etc/hosts entry.)
Compose defines exactly one workspace pair — bootstrap scaffolding, so a fresh install has something to log into and something for the provisioner to clone. Every other workspace is created from the portal (New workspace) or bun run workspace:create; compose does not grow a service per workspace.
Full walkthrough, including troubleshooting: Running the stack.
For UI iteration, run the cockpit dev server outside docker for hot reload — see packages/cockpit/README.md.
The quick start above builds the engine and cockpit from source. To run the published release images instead — a deploy host, no build toolchain — layer the release overlay and name the version:
export DATARAUM_VERSION=1.2.3 # any tag from a GitHub Release
docker compose \ -f packages/infra/docker-compose.yml -f packages/infra/docker-compose.release.yml \ --env-file packages/infra/.env up -d --wait --no-build
This pulls ghcr.io/dataraum/{dataraum, dataraum-cockpit, dataraum-cockpit-migrate} at that tag. See Deployment for the images, schema/migration handling, and the per-workspace topology.
cd packages/engine && uv sync --group dev && uv run pytest --testmon tests/unit -q. See packages/engine/README.md and packages/engine/CLAUDE.md.cd packages/cockpit && bun install && bun --bun run dev (the --bun flag is required). See packages/cockpit/README.md and packages/cockpit/CLAUDE.md.cd packages/cockpit && DATARAUM_WORKSPACE_ID= METADATA_DATABASE_URL= bun run db:pull:metadata. Re-run after the engine adds/changes SQLAlchemy models.Platform docs live in docs/ (workspace root) and are published via Zensical. Start at docs/index.md, or serve the site locally:
uv run --project packages/engine zensical serve # run from the repo root
Apache 2.0 — see LICENSE.