mcpField
O
Open MCP Client

Open MCP Client

github.com/copilotkitFrameworks & SDKs1.7kUpdated 79w ago
Repository

About Open MCP Client

Open MCP Client is an open source project under the MIT License, split into a frontend for the user interface and an agent for core functionality. It needs OpenAI and LangSmith API keys to run.

Key features

  1. 01Frontend handles the user interface
  2. 02Agent service handles core functionality
  3. 03Agent dependencies managed with Poetry
  4. 04Run frontend and agent separately or together
  5. 05OpenAI and LangSmith keys set via .env files

Use cases

  1. 01Set up and debug the frontend and agent locally
  2. 02Open the app in a browser at localhost:3000

Details

From the project README

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.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.