Happy slice of mcp pizzaMCP.pizza

open-multi-agent-canvas

MCP.Pizza Chef: CopilotKit

This open-source chat canvas from CopilotKit runs several helper agents in one conversation: a travel planner, a researcher, and a general agent you can point at tool servers you choose. It is no longer developed here — the maintainers moved it into the main CopilotKit repository under examples, leaving this copy for reference. Running it means installing and building it yourself, plus a free Copilot Cloud key.

Deprecated · moved into the main CopilotKit repository under examples
Communication
Web/Research

Use This MCP client To

Plan a multi-city trip in a live chat canvas Watch several helper agents work in one conversation Research a topic with the findings laid out visually Point the chat at public tool servers I choose Try out agent ideas without building a chat app first

README

Open Multi-Agent Canvas

CopilotKit-Banner

multi-agent-canvas

Open Multi-Agent Canvas, created by CopilotKit is an open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation. It's built with Next.js, LangGraph, and CopilotKit to help with travel planning, research, and general-purpose tasks through MCP servers.

Existing Agents

Check out these awesome agents (they live in separate repositories). You can run them separately or deploy them on LangSmith:

Additionally, this project now includes a built-in MCP (Multi-Channel Protocol) Agent:

  • MCP Agent: A general-purpose agent capable of handling various tasks through configurable MCP servers.

Copilot Cloud is required to run this project:

Quick Start 🚀

1. Prerequisites

Make sure you have:

2. API Keys

Running the Frontend

Rename the example.env file in the frontend folder to .env:

NEXT_PUBLIC_CPK_PUBLIC_API_KEY=...

Install dependencies:

cd frontend
pnpm i

Need a CopilotKit API key? Get one here.

Then, fire up the Next.js project:

pnpm run build && pnpm run start

MCP Agent Setup

mcp-demo

The MCP Agent allows you to connect to various MCP-compatible servers:

  1. Configuring Custom MCP Servers:

    • Click the "MCP Servers" button in the top right of the interface
    • Add servers via the configuration panel:
      • Standard IO: Run commands locally (e.g., Python scripts)
      • SSE: Connect to external MCP-compatible servers (via Server-Sent Events)

  2. Public MCP Servers:

Running the MCP Agent Backend (Optional)

Rename the example.env file in the agent folder to .env:

OPENAI_API_KEY=...
LANGSMITH_API_KEY=...

If you want to use the included MCP Agent with the built-in math server:

cd agent
poetry install
poetry run langgraph dev --host localhost --port 8123 --no-browser

Running a tunnel

Add another terminal and select Remote Endpoint. Then select Local Development. Once this is done, copy the command into your terminal and change the port to match the LangGraph server 8123 image

Documentation

License

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

Note: This project has been consolidated into the CopilotKit monorepo. The latest version lives at examples/showcases/multi-agent-canvas. Please open issues and pull requests in the main CopilotKit repository.

open-multi-agent-canvas FAQ

Is this still maintained?
No — it moved into the main CopilotKit repository at examples/showcases/multi-agent-canvas, and issues belong there now.
Should I use this copy or the new one?
Use the version inside the CopilotKit repository; this one is kept only for reference.
Which apps does it work in?
None — it is its own chat app that you run yourself, not an add-on for Claude or Cursor.
Do I need an account key?
Yes — a free Copilot Cloud key, plus extra keys if you also run the backend agent.
Can I use this to plan a holiday?
Yes — a built-in travel agent handles itineraries, though you should run the newer version instead.
How hard is setup?
You install and build it on your own machine, so expect a developer-level setup.