feat: add MCP: elevenlabs & firecrawl & youtube-transcript

This commit is contained in:
Sun-ZhenXing
2025-10-23 14:07:02 +08:00
parent 5c3fc0f844
commit bd84484bcc
14 changed files with 508 additions and 35 deletions

View File

@@ -0,0 +1,10 @@
# MCP YouTube Transcript Configuration
# Image version
MCP_YOUTUBE_TRANSCRIPT_VERSION=latest
# Port override (default: 8000)
MCP_YOUTUBE_TRANSCRIPT_PORT_OVERRIDE=8000
# Timezone
TZ=UTC

View File

@@ -0,0 +1,53 @@
# MCP YouTube Transcript Server
Model Context Protocol (MCP) server for fetching YouTube video transcripts. Enables AI assistants to retrieve and process YouTube video captions and transcripts.
## Features
- **Transcript Extraction**: Fetch transcripts from YouTube videos
- **Multiple Language Support**: Access transcripts in different languages
- **Automatic Captions**: Support for auto-generated captions
- **Timestamp Information**: Retrieve transcript with timing data
- **MCP Integration**: Standard MCP protocol for AI assistant integration
## Environment Variables
| Variable | Description | Default |
| -------------------------------------- | -------------------- | -------- |
| `MCP_YOUTUBE_TRANSCRIPT_VERSION` | Docker image version | `latest` |
| `MCP_YOUTUBE_TRANSCRIPT_PORT_OVERRIDE` | Host port override | `8000` |
| `TZ` | Timezone | `UTC` |
## Quick Start
1. Copy `.env.example` to `.env`:
```bash
cp .env.example .env
```
2. Start the service:
```bash
docker compose up -d
```
3. Check service status:
```bash
docker compose ps
```
4. View logs:
```bash
docker compose logs -f
```
## Usage
Connect your AI assistant to the MCP server at `http://localhost:8000` to enable YouTube transcript retrieval capabilities.
## License
Please check the official [MCP YouTube Transcript](https://hub.docker.com/r/mcp/youtube-transcript) documentation for license information.

View File

@@ -0,0 +1,53 @@
# MCP YouTube Transcript 服务器
Model Context ProtocolMCP服务器用于获取 YouTube 视频字幕。使 AI 助手能够检索和处理 YouTube 视频字幕和转录内容。
## 功能特性
- **字幕提取**:从 YouTube 视频中获取字幕
- **多语言支持**:访问不同语言的字幕
- **自动字幕**:支持自动生成的字幕
- **时间戳信息**:检索带有时间数据的字幕
- **MCP 集成**:标准 MCP 协议,用于 AI 助手集成
## 环境变量
| 变量 | 描述 | 默认值 |
| -------------------------------------- | --------------- | -------- |
| `MCP_YOUTUBE_TRANSCRIPT_VERSION` | Docker 镜像版本 | `latest` |
| `MCP_YOUTUBE_TRANSCRIPT_PORT_OVERRIDE` | 主机端口覆盖 | `8000` |
| `TZ` | 时区 | `UTC` |
## 快速开始
1. 复制 `.env.example``.env`
```bash
cp .env.example .env
```
2. 启动服务:
```bash
docker compose up -d
```
3. 检查服务状态:
```bash
docker compose ps
```
4. 查看日志:
```bash
docker compose logs -f
```
## 使用说明
将您的 AI 助手连接到 MCP 服务器 `http://localhost:8000`,即可启用 YouTube 字幕检索功能。
## 许可证
请查看官方 [MCP YouTube Transcript](https://hub.docker.com/r/mcp/youtube-transcript) 文档以获取许可证信息。

View File

@@ -0,0 +1,31 @@
x-default: &default
restart: unless-stopped
logging:
driver: json-file
options:
max-size: "100m"
max-file: "3"
deploy:
resources:
limits:
cpus: '1.00'
memory: 512M
reservations:
cpus: '0.25'
memory: 128M
services:
mcp-youtube-transcript:
<<: *default
image: mcp/youtube-transcript:${MCP_YOUTUBE_TRANSCRIPT_VERSION:-latest}
container_name: mcp-youtube-transcript
environment:
- TZ=${TZ:-UTC}
ports:
- "${MCP_YOUTUBE_TRANSCRIPT_PORT_OVERRIDE:-8000}:8000"
healthcheck:
test: ["CMD", "wget", "--quiet", "--tries=1", "--spider", "http://localhost:8000/health"]
interval: 30s
timeout: 10s
retries: 3
start_period: 10s