LangChain MCP Chat Platform

by BilalAltundag

189 downloads Not rated yet

GitHub

About

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

Explore

- 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

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:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
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.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

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

JSON

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

JSON

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

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

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

JSON

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

JSON

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

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

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

JSON

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

JSON

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

From the repository

python -m venv venv

Make sure to use the exact versions in requirements.txt to avoid compatibility issues:

bash
pip install -r requirements.txt



> Important: If you encounter any dependency errors, try installing packages one by one:

>

bash
> pip install fastapi==0.104.1 uvicorn==0.24.0
> pip install langchain==0.3.23 langchain-community==0.3.21 langchain-core==0.3.51
> pip install langchain-mcp-adapters==0.0.7 langchain-google-genai==2.1.2
> pip install langgraph==0.3.29 langgraph-prebuilt==0.1.5 langgraph-sdk==0.1.61
>

If you want to use Tavily search or Gmail features, you'll need to install Node.js and the Smithery CLI:

bash

npm install -g @smithery/cli



Copy the example .env file and edit it with your API keys:

bash

If you don't want to use an .env file, you can directly set the API keys in code:

Open web_js/main.py and replace the environment variable loading with direct assignment:
```python

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"
        ]
    }
}

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

Features

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

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

Email sign in

No reviews posted yet.

About

Explore

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

Features

Project Structure

Setup and Installation

Step 1: Clone the Repository

Step 2: Create and Activate Virtual Environment

More like this

Context 7

1Panel

🔎 GPT Researcher

Serena