Langgraph MCP Client

🚀 Langchain-MCP Client for PostgreSQL Example

This repository presents a very basic example demonstrating how to interact with an MCP server running in a Docker image, which is connected to a PostgreSQL database for use by the LangGraph proxy.

model context protocol

MCP is an open protocol that standardizes the way applications provide context to LLMs. Imagine MCP as the USB-C port for AI applications. Just as USB-C provides a universal interface for your devices to connect to various peripherals and accessories, MCP offers a universal interface for AI models to connect to different data sources and tools.

🚀 Quick Start

Prerequisites

Before you begin, make sure you have the following software installed:

• Docker
• PostgreSQL Database - up and running with data populated
• MCP Server

Process and Tools

• We use a PostgreSQL database that is configured to be visible to the Postgresl MCP server.
• from langchain_mcp_adapters.tools import load_mcp_tools creates MCP tools.
• create_react_agent is a quick proxy templater.
• We stream the output to a file.

Project Setup Instructions

1. Clone the Repository

Clone this repository to your local machine:

git clone https://github.com/your-repo/Langchain-MCP.git
cd Langgraph-mcp-client

2. Create a .env File

Create a .env file in the root directory of the repository, containing the following variables:

DB_HOST=<your database host>
DB_PORT=<your database port>
DB_USER=<your database username>
DB_PASSWORD=<your database password>
DB_NAME=<your database name>

Replace the placeholders with the actual database and MCP server connection information.

3. Install the UV Package

If you haven't already, install the UV package globally: astral uv

MCP Server Setup

1. Clone the MCP Server to a separate directory.
2. Run - docker build -t mcp/postgres -f src/postgres/Dockerfile . to build and tag the image.

Usage Instructions

1. Synchronize the UV Package

Run the following command to synchronize the UV package:

uv sync

This command ensures that the UV package is installed correctly.

2. Run the Query Agent

• Start the query agent using the following command:

uv run queryagent

This will prompt you to enter a user query.

• Alternative - with a query (bank database):

uv run queryagent "Who holds the most funds in their account?"

📋 To-Do List

• Output formatting
• Multi-agent support

🔧 Troubleshooting

• Database connection: Check if the .env file contains the correct database credentials.
• UV package errors: Ensure that the UV CLI is installed globally and that the uv sync command completes without errors.

🤝 Contribution

Feel free to open an issue or submit a pull request to improve this repository.

📄 License

This project is licensed under the MIT License. For more details, please refer to the LICENSE file.