# 💯 YouTube Transcript + YouTube Search MCP for AI Agents

Hosted MCP server providing YouTube transcripts and video search for AI agents. Helps models parse video content without manual transcript scraping.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 13
- Author: ZeroPointRepo
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ZeroPointRepo/youtube-mcp
- Updated: 2026-09-21
- HTML: https://affpapa.org/en/nevibecode/mcp/youtube-transcript-youtube-search-mcp-for-ai-agents

## What it does

The server runs via an HTTP endpoint at `https://transcriptapi.com/mcp`. You do not need to install local runtimes or scrapers. It exposes 12 tools for fetching timestamped transcripts and searching videos. Tracking recent channel uploads uses RSS feeds without consuming search quota.

The repository adheres to the Agent Plugins 1.0.0 layout and bundles a `skills/youtube/SKILL.md` guide. This skill directs the model on which tool to invoke and prevents unnecessary credit usage. The first 100 credits are free. Authentication relies on OAuth 2.1 or an API key from the TranscriptAPI dashboard. Accounts do not require a credit card upfront, but requests beyond the free allowance require paid balance.

## Requirements
- Remote server: `https://transcriptapi.com/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http youtube-transcript-and-youtube-search https://transcriptapi.com/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add youtube-transcript-youtube-search-mcp-for-ai-agents --url https://transcriptapi.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "youtube-transcript-youtube-search-mcp-for-ai-agents": {
            "url": "https://transcriptapi.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "youtube-transcript-youtube-search-mcp-for-ai-agents": {
            "type": "http",
            "url": "https://transcriptapi.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http youtube-transcript-youtube-search-mcp-for-ai-agents https://transcriptapi.com/mcp
```

## When to use it
- fetch timestamped YouTube transcripts directly into agent context
- search YouTube videos and channel catalogs from prompt
- track latest channel uploads via RSS feeds
- extract video lists from playlists without local scrapers

## Example prompts
- Summarize this video using its transcript: https://youtu.be/UF8uR6Z6KLc
- Check what @TED published this month and summarize the top video
- Search for recent lectures on compilers and outline the main points

## Similar
- [mcp-youtube-transcript](https://affpapa.org/en/nevibecode/mcp/mcp-youtube-transcript.md) — MCP server · ★ 492
- [baoyu-youtube-transcript](https://affpapa.org/en/nevibecode/skills/baoyu-youtube-transcript.md) — skill · 21600 installs
- [youtube-transcript](https://affpapa.org/en/nevibecode/skills/youtube-transcript.md) — skill · 3400 installs
- [YouTube Transcript + YouTube Search MCP](https://affpapa.org/en/nevibecode/mcp/youtube-transcript-youtube-search-mcp.md) — MCP server · ★ 22
- [Arcmira: YouTube Transcript Search](https://affpapa.org/en/nevibecode/mcp/arcmira-youtube-transcript-search.md) — MCP server · ★ 76
- [youtube-full](https://affpapa.org/en/nevibecode/skills/youtube-full.md) — skill · 78 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md