MCP ExplorerExplorer

Agentic Ai Mcp Demo

@lloydhamiltonon 9 months ago
2 MIT
FreeCommunity
AI Systems
Demonstrates how to integrate MCP with LangChain using langchain-mcp_connect.

Overview

What is Agentic Ai Mcp Demo

agentic_ai_mcp_demo is a demonstration project that showcases the integration of the Anthropic Model Context Protocol (MCP) with LangChain, allowing developers to connect to MCP servers and utilize various tools within the LangChain ecosystem.

Use cases

Use cases for agentic_ai_mcp_demo include building chatbots, enhancing AI-driven applications, and developing tools that require sophisticated language understanding and generation.

How to use

To use agentic_ai_mcp_demo, you need to set up your environment by providing personal access tokens for GitHub and OpenAI. You can either export these tokens in your terminal or create a .env file. After installation, you can run the demo using the command ‘uv run src/main.py’.

Key features

Key features of agentic_ai_mcp_demo include seamless integration with MCP servers, access to a variety of pre-built tools, and the ability to enhance language model capabilities through the LangChain framework.

Where to use

agentic_ai_mcp_demo can be used in fields such as natural language processing, AI development, and any application requiring advanced language model functionalities.

Content

Langchain Model Context Protocol Demo

Introduction

This project demonstrates:

  1. How to integrate Anthropic Model Context Protocol (MCP) with LangChain.
  2. How to use the langchain-mcp_-connect package to connect to Model Context Protocol (MCP) servers and access tools that can be made available to LangChain.

The langchain_mcp_connect package allows developers to easily integrate their LLMs with a rich ecosystem of pre-built MCP servers.

Pre-requisites

You will need your personal access tokens for GitHub and OpenAI to run this demo.

export GITHUB_PERSONAL_ACCESS_TOKEN=<your_github_personal_access_token>
export OPENAI_API_KEY=<your_openai_api_key>

Or you can create a .env file with the following content:

GITHUB_PERSONAL_ACCESS_TOKEN=<your_github_personal_access_token>
OPENAI_API_KEY=<your_openai_api_key>

Installation

Pre-commit:

pre-commit install

Python env:

uv sync

Running the streaming demo

uv run src/main.py

Tools

No tools

Comments

Recommend MCP Servers

View All MCP Servers