Happy slice of mcp pizzaMCP.pizza

open-mcp-client

MCP.Pizza Chef: CopilotKit

Built by CopilotKit, this is a starter chat interface you run yourself: a web front end with an agent behind it that reaches out to MCP tools. Because you host it, the conversation lives in your own page rather than someone else's app, and you decide which tools are available. Getting it going means creating two small settings files holding your OpenAI and LangSmith keys, installing Poetry, and starting the front end and the agent.

Coding
Other

Use This MCP client To

Run a chat assistant on my own web page Give a demo assistant only the tools I choose Try out an MCP tool in a chat I control Keep customer conversations inside my own product Start a custom assistant project from working code

README

Open MCP Client

CopilotKit-Banner

demospreadsheet.1.mp4

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.

open-mcp-client FAQ

Can I install this and use it straight away?
Not quite. It is a starter project you run yourself, so expect some setup.
What keys do I need?
An OpenAI key and a LangSmith key, added to two small settings files.
Can I use this to put a chat assistant on my own site?
Yes, that is the point of it, and the front end is yours to change.
What has to be installed first?
Poetry for the agent side, and a Node package manager for the front end.
Where does it run?
On your own machine while you develop, at a local web address in your browser.
Is it free?
The code is open source under the MIT licence, though the model provider you connect will have its own costs.