alexsun/compose-anything
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source
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
Download Patch File Download Diff File Expand all files Collapse all files

14
mcp-servers/elevenlabs/.env.example Normal file
View File

@@ -0,0 +1,14 @@
# MCP ElevenLabs Configuration
# Image version
MCP_ELEVENLABS_VERSION=latest
# Port override (default: 8000)
MCP_ELEVENLABS_PORT_OVERRIDE=8000
# ElevenLabs API Key (required)
# Get your API key from https://elevenlabs.io
ELEVENLABS_API_KEY=your_elevenlabs_api_key_here
# Timezone
TZ=UTC

57
mcp-servers/elevenlabs/README.md Normal file
View File

@@ -0,0 +1,57 @@
# MCP ElevenLabs Server
Model Context Protocol (MCP) server for ElevenLabs text-to-speech API integration. Enables AI assistants to generate high-quality voice audio from text.
## Features
- **Text-to-Speech**: Convert text to natural-sounding speech
- **Multiple Voices**: Access to various voice models
- **Voice Cloning**: Create custom voice profiles
- **Multi-language Support**: Support for multiple languages
- **Audio Controls**: Adjust speed, pitch, and stability
- **MCP Integration**: Standard MCP protocol for AI assistant integration
## Environment Variables
| Variable | Description | Default |
| ------------------------------ | ----------------------------- | -------- |
| `MCP_ELEVENLABS_VERSION` | Docker image version | `latest` |
| `MCP_ELEVENLABS_PORT_OVERRIDE` | Host port override | `8000` |
| `ELEVENLABS_API_KEY` | ElevenLabs API key (required) | - |
| `TZ` | Timezone | `UTC` |
## Quick Start
1. Copy `.env.example` to `.env`:
```bash
cp .env.example .env
```
2. Edit `.env` and set your `ELEVENLABS_API_KEY` (get from <https://elevenlabs.io>)
3. Start the service:
```bash
docker compose up -d
```
4. Check service status:
```bash
docker compose ps
```
5. View logs:
```bash
docker compose logs -f
```
## Usage
Connect your AI assistant to the MCP server at `http://localhost:8000` to enable text-to-speech capabilities with ElevenLabs.
## License
Please check the official [MCP ElevenLabs](https://hub.docker.com/r/mcp/elevenlabs) documentation for license information.

57
mcp-servers/elevenlabs/README.zh.md Normal file
View File

@@ -0,0 +1,57 @@
# MCP ElevenLabs 服务器
Model Context Protocol（MCP）服务器,用于 ElevenLabs 文本转语音 API 集成。使 AI 助手能够从文本生成高质量的语音音频。
## 功能特性
- **文本转语音**:将文本转换为自然流畅的语音
- **多种声音**:访问各种语音模型
- **语音克隆**:创建自定义语音配置文件
- **多语言支持**:支持多种语言
- **音频控制**:调整速度、音高和稳定性
- **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_ELEVENLABS_VERSION` | Docker 镜像版本 | `latest` |
| `MCP_ELEVENLABS_PORT_OVERRIDE` | 主机端口覆盖 | `8000` |
| `ELEVENLABS_API_KEY` | ElevenLabs API 密钥（必需） | - |
| `TZ` | 时区 | `UTC` |
## 快速开始
1. 复制 `.env.example` 到 `.env`:
```bash
cp .env.example .env
```
2. 编辑 `.env` 并设置您的 `ELEVENLABS_API_KEY`（从 <https://elevenlabs.io> 获取）
3. 启动服务:
```bash
docker compose up -d
```
4. 检查服务状态:
```bash
docker compose ps
```
5. 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 ElevenLabs 的文本转语音功能。
## 许可证
请查看官方 [MCP ElevenLabs](https://hub.docker.com/r/mcp/elevenlabs) 文档以获取许可证信息。

32
mcp-servers/elevenlabs/docker-compose.yaml Normal file
View File

@@ -0,0 +1,32 @@
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-elevenlabs:
<<: *default
image: mcp/elevenlabs:${MCP_ELEVENLABS_VERSION:-latest}
container_name: mcp-elevenlabs
environment:
- TZ=${TZ:-UTC}
- ELEVENLABS_API_KEY=${ELEVENLABS_API_KEY}
ports:
- "${MCP_ELEVENLABS_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

14
mcp-servers/firecrawl/.env.example Normal file
View File

@@ -0,0 +1,14 @@
# MCP Firecrawl Configuration
# Image version
MCP_FIRECRAWL_VERSION=latest
# Port override (default: 8000)
MCP_FIRECRAWL_PORT_OVERRIDE=8000
# Firecrawl API Key (required)
# Get your API key from https://firecrawl.dev
FIRECRAWL_API_KEY=your_firecrawl_api_key_here
# Timezone
TZ=UTC

57
mcp-servers/firecrawl/README.md Normal file
View File

@@ -0,0 +1,57 @@
# MCP Firecrawl Server
Model Context Protocol (MCP) server for Firecrawl web scraping and crawling capabilities. Enables AI assistants to extract structured data from websites.
## Features
- **Web Scraping**: Extract content from web pages
- **Site Crawling**: Crawl entire websites systematically
- **Structured Data**: Convert web content to structured formats
- **JavaScript Rendering**: Support for dynamic content
- **Rate Limiting**: Built-in rate limiting for respectful scraping
- **MCP Integration**: Standard MCP protocol for AI assistant integration
## Environment Variables
| Variable | Description | Default |
| ----------------------------- | ---------------------------- | -------- |
| `MCP_FIRECRAWL_VERSION` | Docker image version | `latest` |
| `MCP_FIRECRAWL_PORT_OVERRIDE` | Host port override | `8000` |
| `FIRECRAWL_API_KEY` | Firecrawl API key (required) | - |
| `TZ` | Timezone | `UTC` |
## Quick Start
1. Copy `.env.example` to `.env`:
```bash
cp .env.example .env
```
2. Edit `.env` and set your `FIRECRAWL_API_KEY` (get from <https://firecrawl.dev>)
3. Start the service:
```bash
docker compose up -d
```
4. Check service status:
```bash
docker compose ps
```
5. View logs:
```bash
docker compose logs -f
```
## Usage
Connect your AI assistant to the MCP server at `http://localhost:8000` to enable web scraping and crawling capabilities.
## License
Please check the official [MCP Firecrawl](https://hub.docker.com/r/mcp/firecrawl) documentation for license information.

57
mcp-servers/firecrawl/README.zh.md Normal file
View File

@@ -0,0 +1,57 @@
# MCP Firecrawl 服务器
Model Context Protocol（MCP）服务器，用于 Firecrawl 网页抓取和爬虫功能。使 AI 助手能够从网站中提取结构化数据。
## 功能特性
- **网页抓取**:从网页中提取内容
- **网站爬虫**:系统地爬取整个网站
- **结构化数据**:将网页内容转换为结构化格式
- **JavaScript 渲染**:支持动态内容
- **速率限制**:内置速率限制,实现礼貌的抓取
- **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_FIRECRAWL_VERSION` | Docker 镜像版本 | `latest` |
| `MCP_FIRECRAWL_PORT_OVERRIDE` | 主机端口覆盖 | `8000` |
| `FIRECRAWL_API_KEY` | Firecrawl API 密钥（必需） | - |
| `TZ` | 时区 | `UTC` |
## 快速开始
1. 复制 `.env.example` 到 `.env`:
```bash
cp .env.example .env
```
2. 编辑 `.env` 并设置您的 `FIRECRAWL_API_KEY`（从 <https://firecrawl.dev> 获取）
3. 启动服务:
```bash
docker compose up -d
```
4. 检查服务状态:
```bash
docker compose ps
```
5. 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`,即可启用网页抓取和爬虫功能。
## 许可证
请查看官方 [MCP Firecrawl](https://hub.docker.com/r/mcp/firecrawl) 文档以获取许可证信息。

32
mcp-servers/firecrawl/docker-compose.yaml Normal file
View File

@@ -0,0 +1,32 @@
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-firecrawl:
<<: *default
image: mcp/firecrawl:${MCP_FIRECRAWL_VERSION:-latest}
container_name: mcp-firecrawl
environment:
- TZ=${TZ:-UTC}
- FIRECRAWL_API_KEY=${FIRECRAWL_API_KEY}
ports:
- "${MCP_FIRECRAWL_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

10
mcp-servers/youtube-transcript/.env.example Normal file
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

53
mcp-servers/youtube-transcript/README.md Normal file
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.

53
mcp-servers/youtube-transcript/README.zh.md Normal file
View File

@@ -0,0 +1,53 @@
# MCP YouTube Transcript 服务器
Model Context Protocol（MCP）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` 到 `.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。

31
mcp-servers/youtube-transcript/docker-compose.yaml Normal file
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