Open Multi-Agent Canvas
@CopilotKit
About Open Multi-Agent Canvas
The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research
Basic information
Config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Open Multi-Agent Canvas?
Open Multi-Agent Canvas is an open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation. Built with Next.js, LangGraph, and CopilotKit, it supports travel planning, research, and general-purpose tasks through MCP servers.
How to use Open Multi-Agent Canvas?
Clone the repository, rename example.env to .env in the frontend folder and set NEXT_PUBLIC_CPK_PUBLIC_API_KEY from Copilot Cloud, install dependencies with pnpm i, then build and start with pnpm run build && pnpm run start. Optionally run the MCP Agent backend using Poetry and LangGraph.
Key features of Open Multi-Agent Canvas
- Manage multiple agents in one dynamic conversation
- Built-in MCP Agent for general-purpose tasks
- Connect to custom MCP servers via Stdio or SSE
- Public MCP server integration (e.g., mcp.composio.dev)
- Supports travel planning and AI research agents
- Open-source under MIT License
Use cases of Open Multi-Agent Canvas
- Run multiple AI agents simultaneously for travel planning
- Conduct web research with specialized researcher agents
- Integrate custom MCP tools for task automation
- Deploy in collaborative environments for multi-agent workflows
FAQ from Open Multi-Agent Canvas
What is Open Multi-Agent Canvas and how does it differ from single-agent chats?
Open Multi-Agent Canvas allows multiple agents to interact in one conversation, enabling complex multi-step workflows that a single agent cannot handle.
What are the runtime requirements?
You need Node.js, pnpm, and a Copilot Cloud API key. The optional MCP Agent backend requires Python, Poetry, and an OpenAI API key.
Where does my data live?
Data is processed through Copilot Cloud and the configured MCP servers; refer to CopilotKit and MCP documentation for data handling details.
What transport and authentication methods are supported?
MCP servers can be connected via Standard IO (local commands) or SSE (Server-Sent Events). Authentication uses API keys for Copilot Cloud, OpenAI, and LangSmith.
Can I use existing agents with Open Multi-Agent Canvas?
Yes, the project includes reference agents for travel and AI research, and you can add custom agents through the MCP Agent configuration.
More AI & Agents MCP servers
mcp-hfspace MCP Server 🤗
evalstateMCP Server to Use HuggingFace spaces, easy configuration and Claude Desktop mode.
MCP Manager for Claude Desktop
zueaisimple web ui to manage mcp (model context protocol) servers in the claude app
Model Context Protocol for Unreal Engine
chongdashuEnable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).
Gemini MCP Server
aliargunMCP server implementation for Google's Gemini API
Web Agent Protocol
OTA-Tech-AI🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
Comments