Use This MCP client To

Coordinate multiple AI agents for complex research tasks Manage travel planning with specialized multi-agent workflows Integrate diverse MCP servers for enriched multi-agent conversations Deploy and orchestrate AI agents in a unified chat interface Facilitate collaborative problem-solving with multiple AI agents Run and manage separate agents from a single client interface

README

Open 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:

pnpm

2. API Keys

Copilot Cloud

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

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

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)
Public MCP Servers:
- You can connect to public MCP servers like mcp.composio.dev and mcp.run

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

Documentation

License

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

open-multi-agent-canvas FAQ

How do I add new agents to the Open Multi-Agent Canvas?

You can add new agents by integrating MCP servers into the client and configuring them within the interface, allowing dynamic multi-agent management.

Can I use Open Multi-Agent Canvas for real-time collaboration between agents?

Yes, it supports managing multiple agents in one dynamic conversation for real-time collaborative workflows.

What technologies is Open Multi-Agent Canvas built with?

It is built using Next.js, LangGraph, and CopilotKit, enabling robust multi-agent orchestration.

Is Open Multi-Agent Canvas compatible with existing MCP servers?

Yes, it is designed to integrate seamlessly with various MCP servers for extended functionality.

Can I deploy agents managed by Open Multi-Agent Canvas on other platforms?

Yes, agents can be run separately or deployed on platforms like LangSmith for broader use.

Does Open Multi-Agent Canvas support general-purpose tasks?

Yes, it supports a wide range of tasks including travel planning, research, and more through multi-agent collaboration.

How does Open Multi-Agent Canvas enhance multi-agent workflows?

By providing a unified interface to manage and coordinate multiple agents, it simplifies complex task execution and research.

Is the Open Multi-Agent Canvas open source?

Yes, it is fully open source and available on GitHub for community contributions and customization.