MCP Template Server

Template MCP server providing OpenAI, Anthropic, and EnrichB2B integrations for prompts, completions, and LinkedIn data retrieval.

python

1

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "moonlabsai-enrich_b2b_mcp": {
      "command": "python",
      "args": [
        "server.py"
      ]
    }
  }
}

You are deploying a template MCP server that integrates OpenAI, Anthropic, and EnrichB2B data to power contextual AI prompts. It runs as an MCP server you can query from any MCP client, enabling you to generate text, analyze content, and enrich LinkedIn data through modular tools and prompts.

How to use

Connect with the MCP server from an MCP client using the standard MCP workflow. You can start the server in development mode and then issue requests to generate text, fetch profile details, retrieve recent activities, or run analysis prompts. The server exposes endpoints and tools that map to the following capabilities: config://app to obtain server configuration, get_profile_details to fetch LinkedIn profile information, get_contact_activities to fetch a profile’s recent posts and activities, gpt4_completion to generate text with GPT-4, claude_completion to generate text with Claude, and analysis_prompt as a text analysis template. The EnrichB2B integration provides specific tools for LinkedIn data enrichment.

How to install

Preinstall prerequisites: Python 3.8+ and a compatible package manager (pip). You also need a virtual environment utility available on your system.

Step by step commands you should run in your project root:

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

pip install -r requirements.txt

cp .env.example .env

Edit the newly created .env file to configure your API keys and other settings. Save the file when you are done.

## Configuration and running the server

Start the server in development mode with Python directly or via the MCP CLI. Both approaches run the MCP server locally for testing and development.

python server.py

mcp dev server.py

## Notes on usage and capabilities

The server is built with FastAPI and Uvicorn, exposing a structured project layout and example resources to help you explore tools and prompts. The EnrichB2B integration provides `get_profile_details` and `get_contact_activities` endpoints to fetch LinkedIn data for enrichment workflows. Use the provided prompts and resources to tailor your AI interactions for market research, outreach, or profile analysis.

## Available tools

### config://app

Fetch server configuration data and runtime settings to understand how the MCP server is configured and what resources are available.

### get\_profile\_details

Retrieve detailed information about a LinkedIn profile, including optional company details and follower counts.

### get\_contact\_activities

Fetch recent activities and posts from a LinkedIn profile, with controls for page count and interaction counts per post.

### gpt4\_completion

Generate text using the GPT-4 model for prompts and content creation.

### claude\_completion

Generate text using the Claude model for alternative AI completions.

### analysis\_prompt

Provide a template prompt for text analysis tasks and insights generation.