MCP ExplorerExplorer

Open MCP Client

@CopilotKiton 3 days ago
1508 MIT
FreeCommunity
AI Systems
Open MCP Client: A setup guide for integrating with Langsmith and OpenAI APIs.

Overview

What is Open MCP Client

Open MCP Client is a software solution designed to facilitate interactions between a user-friendly frontend interface and a robust agent backend. It utilizes various APIs to enhance functionality and streamline processes.

Use cases

The Open MCP Client can be used in applications requiring conversational AI, customer support automation, data analysis, and other functionalities that benefit from AI-driven solutions. It serves industries such as tech support, e-commerce, and any domain requiring interactive user engagement.

How to use

To get started, set up environment variables by creating .env files in the root and agent folders. Install necessary dependencies using Poetry, and run the frontend and agent concurrently or separately. Access the application through a web browser at http://localhost:3000.

Key features

Key features include a modular architecture that separates frontend and agent functionalities, easy setup with environment variable configuration, dependency management through Poetry, and simultaneous service running capabilities for development convenience.

Where to use

Open MCP Client can be deployed in web applications, customer support systems, and any scenario that benefits from AI capabilities, making it suitable for businesses looking to integrate advanced conversational AI into their platforms.

Content

Open MCP Client

CopilotKit-Banner

https://github.com/user-attachments/assets/364b6705-14d4-4e6d-bea7-fb9f12664fab

Getting Started

Set Up Environment Variables

Create a .env file at the root of your project:

touch .env

Add the following to .env:

LANGSMITH_API_KEY=lsv2_...
OPENAI_API_KEY=sk-...

Next, navigate to the agent folder and create another .env file:

cd agent
touch .env

Add the following inside agent/.env:

OPENAI_API_KEY=sk-...
LANGSMITH_API_KEY=lsv2_...

Set Up Poetry:

Poetry manages dependencies for the agent service. Install it with:

pip install poetry

Verify the installation by running:

poetry --version

Development

For easier debugging, run the frontend and agent in separate terminals:

# Terminal 1 - Frontend
pnpm run dev-frontend

# Terminal 2 - Agent
pnpm run dev-agent

Alternatively, launch both services together:

pnpm run dev

Visit http://localhost:3000 in your browser to view the application.

Architecture

The codebase is organized into two primary components:

  • Frontend - Handles the user interface.
  • Agent - Manages the core functionality.

License

Distributed under the MIT License. See LICENSE for more info.

Tools

No tools

Comments