by flowith-ai · MCP Server · ★ 39
Canvas Cowork Cowork on a spatial canvas from the CLI — create canvases, generate images/text/video/agent responses, read results, recall past work, and manage nodes on Flowith's shared canvas. Your AI agent gets a live cursor on the canvas. It moves in real time — users see nodes appear and the tree grow.
| Stars | 39 |
| Forks | 3 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 64.2537685062676/100 |
| Last Updated | 2026-06-22 |
| Created | 2026-03-31 |
| Platforms | claude-code, cli, codex, mcp, node |
| Est. Tokens | ~5k |
These tools work well together with canvas-cowork for enhanced workflows:
Explore other popular mcp server tools:
canvas-cowork is Cowork on a spatial canvas from the CLI — create canvases, generate images/text/video/agent responses, read results, recall past work, and manage nodes. It is categorized as a MCP Server with 39 GitHub stars.
canvas-cowork is primarily written in TypeScript. It covers topics such as agent-skills, ai-agent, canvas.
You can find installation instructions and usage details in the canvas-cowork GitHub repository at github.com/flowith-ai/canvas-cowork. The project has 39 stars and 3 forks, indicating an active community.
canvas-cowork is released under the MIT license, making it free to use and modify according to the license terms.