Tech News Update Agent
A FastAPI backend that integrates with ElevenLabs MCP to create an AI agent capable of making outbound calls and delivering friendly, jargon-free tech news updates.
README
ElevenLabs MCP Integration - Tech News Update Agent
A FastAPI backend to create an ElevenLabs agent that makes outbound calls to deliver friendly, jargon-free tech news updates. This project demonstrates the integration of ElevenLabs MCP (Model Context Protocol) for creating conversational AI agents with voice capabilities.
🚀 Features
- Conversational AI Agent: Creates a confident, friendly tech-savvy colleague
- Voice Integration: Uses ElevenLabs Alice voice for natural-sounding calls
- Tech News Delivery: Provides updates about AI, programming, and cybersecurity
- Simple API: Easy-to-use endpoints for agent creation and call management
- MCP Integration: Leverages ElevenLabs MCP for seamless agent management
📁 Project Structure
ElevenLabs/
├── app/
│ ├── main.py # FastAPI application with endpoints
│ ├── elevenlabs_client.py # ElevenLabs API client functions
│ └── config.py # Configuration and environment variables
├── requirements.txt # Python dependencies
├── .env.example # Environment variables template
├── .gitignore # Git ignore rules
└── README.md # Project documentation
🛠️ Setup
Prerequisites
- Python 3.8+
- ElevenLabs API key
- ElevenLabs phone number (for outbound calls)
- Git
Installation
-
Clone the repository
git clone https://github.com/LEKKALAGANESH/Eleven-Labs-MCP-Integration.git cd Eleven-Labs-MCP-Integration -
Install dependencies
pip install -r requirements.txt -
Configure environment variables
cp .env.example .env # Edit .env with your actual values -
Run the server
uvicorn app.main:app --reload
🔧 Configuration
Create a .env file with the following variables:
ELEVENLABS_API_KEY=your_elevenlabs_api_key
ELEVENLABS_BASE_URL=https://api.elevenlabs.io/v1
AGENT_VOICE_ID=Xb7hH8MSUJpSbSDYk0k2
AGENT_PHONE_NUMBER_ID=your_phone_number_id
📡 API Endpoints
1. Create Agent
POST /create-agent
Creates a new Tech News Update Agent with predefined personality and voice.
Response:
{
"agent": {
"agent_id": "agent_5701k1capwtse9fske3xgefspyra",
"name": "Tech News Update Agent",
"voice_id": "Xb7hH8MSUJpSbSDYk0k2"
}
}
2. Make Outbound Call
POST /call
Initiates an outbound call to the specified phone number.
Request Body:
{
"phone_number": "+1234567890"
}
Response:
{
"result": {
"conversation_id": "conv_3401k1casackffe9emj08wgf9zsd",
"call_sid": "CA12265951d92ca816f1f15693d7efd6a2",
"status": "success"
}
}
🎯 Usage Examples
Using curl
-
Create the agent:
curl -X POST "http://localhost:8000/create-agent" -
Make a call:
curl -X POST "http://localhost:8000/call" \ -H "Content-Type: application/json" \ -d '{"phone_number": "+1234567890"}'
Using Python requests
import requests
# Create agent
response = requests.post("http://localhost:8000/create-agent")
agent_data = response.json()
agent_id = agent_data["agent"]["agent_id"]
# Make call
call_data = {"phone_number": "+1234567890"}
response = requests.post("http://localhost:8000/call", json=call_data)
print(response.json())
🤖 Agent Personality
The Tech News Update Agent is configured with:
- Tone: Confident, friendly, and conversational
- Voice: Alice (female voice) for natural communication
- Expertise: AI, programming, and cybersecurity updates
- Style: Jargon-free explanations with practical implications
- Approach: Like a knowledgeable colleague sharing interesting news
⚠️ Important Notes
- Phone Verification: You must have a verified or paid ElevenLabs/Twilio account to call unverified numbers
- Agent ID: After creating the agent, update the
agent_idinmain.pywith the returned ID - API Limits: Be aware of ElevenLabs API rate limits and usage quotas
- Environment Variables: Never commit your actual API keys to version control
🔗 Related Links
📝 License
This project is open source and available under the MIT License.
🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
📞 Support
For support, please open an issue in the GitHub repository or contact the maintainers.
Built with ❤️ using ElevenLabs MCP Integration
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。