Skip to content
Back to search

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

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/CopilotKit/open-multi-agent-canvas with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/CopilotKit/open-multi-agent-canvas'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/copilotkit--open-multi-agent-canvas/badge.svg)](/listings/copilotkit--open-multi-agent-canvas)

HTML

<a href="/listings/copilotkit--open-multi-agent-canvas"><img src="/api/listings/copilotkit--open-multi-agent-canvas/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 116 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <div align="center">
  2. # Open Multi-Agent Canvas
  3. ![CopilotKit-Banner](https://github.com/user-attachments/assets/8167c845-0381-45d9-ad1c-83f995d48290)
  4. </div>
  5. ![multi-agent-canvas](https://github.com/user-attachments/assets/5953a5a6-5686-4722-9477-5279b67b3dba)
  6. Open Multi-Agent Canvas, created by [CopilotKit](https://github.com/CopilotKit/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.
  7. ## Existing Agents
  8. Check out these awesome agents (they live in separate repositories). You can run them separately or deploy them on LangSmith:
  9. - [CoAgents Travel Agent](https://github.com/CopilotKit/CopilotKit/tree/main/examples/coagents-travel/agent)
  10. - [CoAgents AI Researcher](https://github.com/CopilotKit/CopilotKit/tree/main/examples/coagents-ai-researcher/agent)
  11. Additionally, this project now includes a built-in MCP (Multi-Channel Protocol) Agent:
  12. - **MCP Agent**: A general-purpose agent capable of handling various tasks through configurable MCP servers.
  13. ## Copilot Cloud is required to run this project:
  14. ## Quick Start 🚀
  15. ### 1. Prerequisites
  16. Make sure you have:
  17. - [pnpm](https://pnpm.io/installation)
  18. ### 2. API Keys
  19. - [Copilot Cloud](https://dashboard.operations.copilotkit.ai)
  20. ## Running the Frontend
  21. Rename the `example.env` file in the `frontend` folder to `.env`:
  22. ```sh
  23. NEXT_PUBLIC_CPK_PUBLIC_API_KEY=...
  24. ```
  25. Install dependencies:
  26. ```sh
  27. cd frontend
  28. pnpm i
  29. ```
  30. Need a CopilotKit API key? Get one [here](https://dashboard.operations.copilotkit.ai/).
  31. Then, fire up the Next.js project:
  32. ```sh
  33. pnpm run build && pnpm run start
  34. ```
  35. ## MCP Agent Setup
  36. ![mcp-demo](./agent/demo/mcp-demo.gif)
  37. The MCP Agent allows you to connect to various MCP-compatible servers:
  38. 1. **Configuring Custom MCP Servers**:
  39. - Click the "MCP Servers" button in the top right of the interface
  40. - Add servers via the configuration panel:
  41. - **Standard IO**: Run commands locally (e.g., Python scripts)
  42. - **SSE**: Connect to external MCP-compatible servers (via Server-Sent Events)
  43. 2. **Public MCP Servers**:
  44. - You can connect to public MCP servers like [mcp.composio.dev](https://mcp.composio.dev/) and [mcp.run](https://www.mcp.run/)
  45. ## Running the MCP Agent Backend (Optional)
  46. Rename the `example.env` file in the `agent` folder to `.env`:
  47. ```sh
  48. OPENAI_API_KEY=...
  49. LANGSMITH_API_KEY=...
  50. ```
  51. If you want to use the included MCP Agent with the built-in math server:
  52. ```sh
  53. cd agent
  54. poetry install
  55. poetry run langgraph dev --host localhost --port 8123 --no-browser
  56. ```
  57. ## Running a tunnel
  58. Add another terminal and select Remote Endpoint.
  59. Then select Local Development.
  60. Once this is done, copy the command into your terminal and change the port to match the LangGraph server `8123`
  61. ![image](https://github.com/user-attachments/assets/6bf41042-9529-4470-8baf-dd076aad31a1)
  62. ## Documentation
  63. - [CopilotKit Docs](https://docs.copilotkit.ai/coagents)
  64. - [LangGraph Platform Docs](https://langchain-ai.github.io/langgraph/cloud/deployment/cloud/)
  65. - [Model Context Protocol (MCP) Docs](https://github.com/langchain-ai/langgraph/tree/main/examples/mcp)
  66. ## License
  67. Distributed under the MIT License. See LICENSE for more info.
  68. ---
  69. > **Note:** This project has been consolidated into the [CopilotKit monorepo](https://github.com/CopilotKit/CopilotKit).
  70. > The latest version lives at [`examples/showcases/multi-agent-canvas`](https://github.com/CopilotKit/CopilotKit/tree/main/examples/showcases/multi-agent-canvas).
  71. > Please open issues and pull requests in the [main CopilotKit repository](https://github.com/CopilotKit/CopilotKit).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.