What is Langgraph Mcp Client

LangGraph-MCP-Client is a client implementation designed to interact with a PostgreSQL MCP Server, facilitating the connection between LangGraph agents and various data sources through the Model Context Protocol (MCP).

Use cases

Use cases include querying financial databases, generating insights from large datasets, and developing AI-driven applications that require real-time data access.

How to use

To use LangGraph-MCP-Client, clone the repository, set up a .env file with your PostgreSQL database credentials, install the UV package, and run the query agent using the provided commands.

Key features

Key features include integration with PostgreSQL, support for the Model Context Protocol, easy setup with Docker, and the ability to create and run query agents for data retrieval.

Where to use

LangGraph-MCP-Client can be used in various fields such as data analysis, AI application development, and any domain requiring interaction with large language models and structured data sources.

Langgraph-MCP Client for Postgresql Example

This repository demonstrates a very low level example of how to interact with an MCP server as a docker image, connected to a PostgreSQL database for LangGraph agents.

model context protocol

MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools.

---

Prerequisites

Before you begin, ensure you have the following installed on your system:

• Docker
• PostgreSQL Database - running and populated
• MCP Servers

---

Flow and tools

• We use a postgresql database that the Postgresl MCP Server is aware of through the config
• from langchain_mcp_adapters.tools import load_mcp_tools creates the mcp tool
• create_react_agent is a fast agent templater
• we output the stream to 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 directory

2. Create a .env File

Create a .env file in the root of the repository with 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 your actual database and MCP server connection details.

3. Install UV Package

Install the UV package globally if you haven’t already:

Astral uv

---

MCP Server Setup

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

Usage Instructions

1. Sync the UV Package

Run the following command to sync the UV package:

uv sync

This command ensures that the UV package installs the package correctly.

2. Run the Query Agent

Start the query agent using the following command:

uv run queryagent

This will prompt for the user query

Alt - with query (Banking database)

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

---

TODO:

• Output formating
• Multi agent

Troubleshooting

• Database Connection: Verify the .env file contains the correct database credentials.
• UV Package Errors: Ensure the UV CLI is installed globally and the uv sync command completes without errors.

---

Contributing

Feel free to open issues or submit pull requests to improve this repository.

---

License

This project is licensed under the MIT License. See the LICENSE file for details.