LangChain MCP Chat Platform

by BilalAltundag

189 downloads
Not rated
GitHub

About

A versatile chat platform that integrates LangChain, custom MCP servers, and various AI models for enhanced chat capabilities.

Details

Author
BilalAltundag
Downloads
189
Categories
AI

- LangChain integration for advanced conversation management and tool usage
- Powered by Google Gemini 2.0 Flash model
- Custom MCP servers: Tavily web search, Gmail, and accounting (muhasebe)
- Conversation history tracking for contextual responses
- Responsive web UI built with FastAPI and WebSockets
- Extensible architecture to add new tools and capabilities

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name LangChain MCP Chat Platform
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Clone the repository, create a Python virtual environment, install dependencies from requirements.txt, set up a .env file with your GOOGLE_API_KEY and SMITHERY_KEY, then run the application from the web_js directory with python main.py. Optionally, enable the Gmail API in Google Cloud Console for email features.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "langchain mcp chat platform": {
            "langchain-mcp-chat-platform": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

McpServers

{
    "langchain-mcp-chat-platform": {
        "command": "python",
        "args": [
            "-m",
            "venv",
            "venv"
        ]
    }
}

LangChain MCP Chat Platform

A versatile chat platform that integrates LangChain, custom MCP (Model Control Protocol) servers, and Google's Gemini AI model for enhanced conversational capabilities.

Ekran Alıntısı

image

Features

- Langchain Integration: Utilize the power of LangChain for advanced conversation management and tool usage
- Google Gemini AI: Powered by Google's powerful Gemini 2.0 Flash model for natural conversations
- Custom MCP Servers: Integrates with various MCP servers for specialized functionalities:
- Tavily web search and extraction (Tavily MCP Link)
> Please check the repository and follow setup instructions for integration.
- Gmail integration for email operations (Gmail MCP GitHub Repo)
> Make sure to clone and configure it as per the instructions to enable Gmail features.
- Custom accounting system (muhasebe)
- Memory Management: Conversation history tracking for contextual responses
- Web Interface: Responsive web UI for user interactions
- Extensible Architecture: Easy to add new tools and capabilities

Project Structure

langchain-mcp-chat-platform/
├── web_js/               # Web interface using FastAPI and WebSockets
│   ├── main.py           # Main FastAPI application with WebSocket connections
│   ├── templates/        # HTML templates
│   └── static/           # Static assets (CSS, JS)
├── own_mcp/              # Custom MCP server implementations
│   ├── mcp_server.py     # Main MCP server implementation
│   ├── muhasebe_client.py # Accounting system client
│   └── __init__.py       # Package initialization
└── app/                  # Desktop application
    ├── main.py           # Main application entry point
    ├── database/         # Database operations
    └── ui/               # UI components

Setup and Installation

Step 1: Clone the Repository

git clone https://github.com/BilalAltundag/langchain-mcp-chat-platform.git
cd langchain-mcp-chat-platform

Step 2: Create and Activate Virtual Environment

```bash
No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.