Skip to main content
Glama

MCP 播客抓取器

一个用于抓取和转录播客剧集的 MCP(模型上下文协议)服务器。专为 Claude Code 或 Claude Desktop 设计——你提供播客,MCP 进行转录,Claude 进行总结。

由 Walid Koleilat 构建,旨在端到端学习 MCP 并解决一个实际工作流:在不离开 Claude 的情况下,将数小时的播客音频转化为有用的、以产品经理为中心的摘要。

功能特点

  • 🎙️ 抓取播客:从 YouTube 视频或 RSS 源抓取

  • 🎯 转录音频:使用 Deepgram 快速的 Nova-2 模型

  • 📁 组织文件:按播客名称和剧集日期分类

  • 🔄 跟踪播客:自动检查新剧集

  • ⏭️ 跳过重复:不会重新抓取已处理的剧集

  • 📋 查找未完成工作:列出需要总结的剧集

  • ✏️ 自定义摘要提示词:根据你的需求自定义 Claude 的总结方式

Related MCP server: ytt-mcp

工作原理

You: "Check for new episodes and summarize them"
         ↓
Claude: Calls check_new_episodes() → Finds new episodes
         ↓
Claude: Calls scrape_podcast() → Downloads & transcribes
         ↓
Claude: Calls get_summary_prompt() → Reads your custom instructions
         ↓
Claude: Calls get_transcript() → Reads the transcript
         ↓
Claude: Summarizes following your prompt
         ↓
Claude: Calls save_summary() → Saves the .md file
         ↓
Done! transcript.md + summary.md saved

安装指南

第 1 步:先决条件

安装所需的系统工具(macOS):

# Install Homebrew if you don't have it
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

# Install yt-dlp (for YouTube) and ffmpeg (for audio)
brew install yt-dlp ffmpeg

第 2 步:克隆与构建

# Clone the repository
git clone https://github.com/walid-koleilat/mcp-podcast-scraper.git
cd mcp-podcast-scraper

# Install dependencies
npm install

# Build
npm run build

第 3 步:获取 Deepgram API 密钥

  1. 前往 https://console.deepgram.com/

  2. 注册(免费层级包含 200 美元额度 - 足以转录约 300 小时的音频)

  3. 创建 API 密钥

  4. 复制该密钥

第 4 步:配置

复制示例配置文件并添加你的 API 密钥:

# Copy the example config
cp config.example.json config.json

# Edit config.json and add your Deepgram API key

你的 config.json 应该如下所示:

{
  "outputDirectory": "./podcasts",
  "deepgramApiKey": "YOUR_ACTUAL_DEEPGRAM_API_KEY",
  "tempDirectory": "./temp"
}

⚠️ 重要提示: 切勿将 config.json 提交到 git - 它包含你的 API 密钥!.gitignore 文件已将其排除。

第 5 步:添加到 Claude Code

将此配置添加到你的 Claude Code MCP 设置中(~/.cursor/mcp.json 或通过 Settings → MCP):

{
  "mcpServers": {
    "podcast-scraper": {
      "command": "node",
      "args": ["/FULL/PATH/TO/mcp-podcast-scraper/dist/index.js"]
    }
  }
}

重要提示: 将 /FULL/PATH/TO/ 替换为你安装目录的实际路径。

第 5 步(替代方案):添加到 Claude Desktop

编辑 ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "podcast-scraper": {
      "command": "node",
      "args": ["/FULL/PATH/TO/mcp-podcast-scraper/dist/index.js"]
    }
  }
}

然后重启 Claude Desktop。


文件结构

mcp-podcast-scraper/
├── config.example.json     # Template - copy to config.json
├── config.json             # Your config (git-ignored, contains API key)
├── tracking.example.json   # Example tracking file
├── tracking.json           # Your tracked podcasts (git-ignored)
├── prompts/
│   └── summary-prompt.md   # Customize how Claude summarizes (editable)
├── podcasts/               # Your transcripts & summaries (git-ignored)
├── src/                    # Source code
├── dist/                   # Compiled code (git-ignored)
└── node_modules/           # Dependencies (git-ignored)

使用示例

抓取特定剧集

"Scrape this YouTube podcast: https://youtube.com/watch?v=..."

"Find and scrape the latest Lex Fridman episode"

跟踪播客以获取新剧集

"Track the Huberman Lab podcast: https://feeds.megaphone.fm/hubermanlab"

"Check my tracked podcasts for new episodes"

"List all podcasts I'm tracking"

查找未完成的工作

"Show me episodes that need summaries"

"List incomplete episodes"

MCP 工具参考

工具

描述

scrape_podcast

抓取并转录剧集。返回文件路径和预览。

get_transcript

读取已抓取剧集的完整转录稿。

get_summary_prompt

获取你的自定义总结指令。

save_summary

将生成的摘要保存为 markdown 文件。

check_new_episodes

检查已跟踪的播客是否有新(未抓取)剧集。

list_incomplete

查找有转录稿但没有摘要的剧集。

search_podcast

搜索 YouTube 或解析 RSS 源以查找剧集。

add_tracking

将播客 RSS 源添加到你的跟踪列表。

list_tracking

列出你正在跟踪的所有播客。

remove_tracking

从你的跟踪列表中移除播客。


工作流

典型会话

  1. 检查新剧集:

    "Check my tracked podcasts for new episodes"
  2. 抓取每个新剧集:

    "Scrape the first one"
  3. 获取转录稿并总结:

    "Get the transcript and summarize it"
  4. 对剩余剧集重复上述步骤

恢复未完成的工作

如果你在会话中途停止:

"Show me episodes that need summaries"

然后针对每个未完成的剧集:

"Get the transcript for [episode] and summarize it"

输出结构

文件按播客和剧集组织:

podcasts/
├── Huberman Lab/
│   ├── 2024-12-10 - Episode Title/
│   │   ├── transcript.md
│   │   └── summary.md
│   └── 2024-12-05 - Another Episode/
│       ├── transcript.md
│       └── summary.md
└── Lex Fridman Podcast/
    └── 2024-12-08 - Guest Name/
        ├── transcript.md
        └── summary.md

配置选项

选项

描述

默认值

outputDirectory

保存转录稿和摘要的位置。可以是相对路径或绝对路径。

./podcasts

deepgramApiKey

用于转录的 Deepgram API 密钥

必需

tempDirectory

音频文件的临时目录(启动时自动清理)

./temp

环境变量(config.json 的可选替代方案):

  • DEEPGRAM_API_KEY

  • OUTPUT_DIRECTORY

  • TEMP_DIRECTORY


自定义摘要提示词

通过编辑 prompts/summary-prompt.md 来控制 Claude 如何总结你的播客。

默认提示词是为 产品经理 量身定制的,包括:

  • 🎯 剧集概述

  • 💡 给产品经理的关键见解

  • 🧠 心智模型与框架

  • 📈 个人成长收获

  • ✅ 行动项

  • 💬 精彩引语

  • 🔗 相关主题

根据你的需求进行自定义

编辑 prompts/summary-prompt.md 以:

  • 更改目标受众(工程师、设计师、创始人等)

  • 添加/删除部分

  • 调整摘要长度

  • 专注于特定主题

  • 更改格式风格

自定义示例:

针对工程师:

Focus on:
- Technical concepts and architecture decisions
- Implementation details worth noting
- Tools and technologies mentioned
- Code patterns and best practices

针对创始人:

Focus on:
- Business strategy insights
- Fundraising advice
- Growth tactics
- Leadership lessons
- Mistakes to avoid

Claude 将在生成每个摘要之前读取此提示词,确保输出的一致性和个性化。


开发

# Watch mode (auto-rebuild on changes)
npm run dev

# Build once
npm run build

# Run MCP server directly
npm start

# Clean build artifacts and temp files
npm run clean

# Test with MCP Inspector (interactive UI)
npx @modelcontextprotocol/inspector node dist/index.js

故障排除

"ffprobe and ffmpeg not found"

brew install ffmpeg

"Deepgram API key not configured"

确保你已将 config.example.json 复制为 config.json 并添加了你的 API 密钥。

MCP 服务器无法连接

  1. 运行 npm run build

  2. 验证 MCP 配置中的路径是否正确

  3. 重启 Claude Code/Desktop

"YouTube URLs not supported for tracking"

请改用 RSS 源。在 https://getrssfeed.com/ 查找播客 RSS 源。


许可证

MIT

Available Tools

10 tools
add_trackingA

Add a podcast RSS feed to the tracking list. Use check_new_episodes to find new episodes.

Inputs: podcastName (required), feedUrl (required).

check_new_episodesB

Check all tracked podcasts for new episodes that haven't been scraped yet

Inputs: no named parameters.

get_summary_promptA

Get the custom prompt/instructions for how to summarize podcasts. Read this before summarizing to follow the user's preferences.

Inputs: no named parameters.

get_transcriptB

Read the transcript of a previously scraped episode. After reading, use get_summary_prompt for summarization instructions.

Inputs: podcastName (required), episodeTitle (required), episodeDate (required).

list_incompleteA

List all episodes that have transcripts but are missing summaries. Use this to find episodes that need summarization.

Inputs: no named parameters.

list_trackingB

List all podcasts currently being tracked

Inputs: no named parameters.

remove_trackingC

Remove a podcast from the tracking list

Inputs: podcastName (required).

save_summaryC

Save your generated summary to a markdown file.

Inputs: podcastName (required), episodeTitle (required), episodeDate (required), summaryText (required).

scrape_podcastA

Scrape a podcast episode and transcribe it. Returns transcript file path. Use get_transcript to read it, then save_summary after summarizing.

Inputs: query (required), podcastName, episodeTitle, force.

search_podcastB

Search for podcasts or episodes on YouTube, or parse an RSS feed URL to see available episodes

Inputs: query (required), source.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 10 tools

    Disambiguation4/5

    Most tools have distinct purposes, but there is some overlap between 'scrape_podcast' and 'check_new_episodes' as both involve scraping episodes, which could cause confusion. However, descriptions clarify that 'scrape_podcast' is for manual scraping of specific episodes, while 'check_new_episodes' automatically checks tracked feeds, so the ambiguity is limited.

    Naming Consistency4/5

    Tool names follow a consistent verb_noun pattern throughout, such as 'add_tracking', 'check_new_episodes', and 'save_summary'. The only minor deviation is 'list_incomplete', which uses an adjective instead of a noun, but this does not significantly impact readability or consistency.

    Tool Count5/5

    With 10 tools, the server is well-scoped for podcast scraping and summarization. Each tool serves a clear purpose in the workflow, from tracking and scraping to transcription and summarization, without being overly sparse or bloated.

    Completeness5/5

    The tool set provides complete coverage for the podcast domain, including tracking management (add, list, remove), scraping and transcription, transcript retrieval, summarization with custom prompts, and saving summaries. There are no obvious gaps; it supports a full lifecycle from discovery to final output.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      An MCP server that enables users to retrieve YouTube transcripts and perform video or channel searches without requiring Google API keys. It supports transcript chunking and provides tools for detailed video content analysis and channel metadata extraction.
      5
      4
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server that extracts YouTube video transcripts (including metadata) as Markdown, enabling AI to summarize and discuss video content without watching it.
      MIT