Enrichb2b

🚀 MCP Template Server

A template server implementing the Model Context Protocol (MCP), integrating OpenAI, Anthropic, and EnrichB2B.

🚀 Quick Start

📦 Installation

1. Create a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

2. Install dependencies:

pip install -r requirements.txt

3. Set environment variables:

cp .env.example .env
# Edit the .env file with your API keys and configurations

🚀 Running the Server

In development mode:

python server.py

Or use the MCP CLI:

mcp dev server.py

✨ Features

• OpenAI GPT-4 integration
• Anthropic Claude integration
• EnrichB2B LinkedIn data integration
• FastAPI and Uvicorn server
• Environment configuration
• Example resources and tools
• Structured project layout

📚 Documentation

📁 Project Structure

.
├── .env.example          # Environment variable template file
├── .gitignore           # Git ignore rules
├── README.md            # This file
├── requirements.txt     # Python dependencies
├── enrichb2b.py        # EnrichB2B API client
└── server.py           # MCP server implementation

💻 Usage Examples

Basic Usage

1. Start the server.
2. Connect using any MCP client.
3. Use the provided tools and resources:
   • config://app - Get server configuration
   • get_profile_details - Get LinkedIn profile information
   • get_contact_activities - Get recent activities and posts of a LinkedIn user
   • gpt4_completion - Generate text using GPT-4
   • claude_completion - Generate text using Claude
   • analysis_prompt - Text analysis template

EnrichB2B Tools

get_profile_details

Get detailed information about a LinkedIn profile:

result = await get_profile_details(
    linkedin_url="https://www.linkedin.com/in/username",
    include_company_details=True,  # Whether to include company details
    include_followers_count=True   # Whether to include the number of followers
)

get_contact_activities

Get recent activities and posts of a LinkedIn user:

result = await get_contact_activities(
    linkedin_url="https://www.linkedin.com/in/username",
    pages=1,  # Number of pages (1 - 50)
    comments_per_post=1,  # Number of comments per post (0 - 50)
    likes_per_post=None   # Number of likes per post (0 - 50)
)

🔧 Development

To add new features:

1. Add new tools using the @mcp.tool() decorator.
2. Add new resources using the @mcp.resource() decorator.
3. Add new prompts using the @mcp.prompt() decorator.

📄 License

MIT