
Whiteboard MCP
io.github.ansuman-shuklaPublished by GitHub account ansuman-shuklav0.3.5Updated Oct 31, 2026
Local Excalidraw whiteboard your coding agent draws on live, and sees what you draw back.
Overview
Local Excalidraw whiteboard server that lets a coding agent draw diagrams on a live board beside the chat and see what you draw back.
- What you can do
- Draw diagrams on a live Excalidraw board next to the chat
- Read the board so the agent can see what the user has drawn
- Run locally as a token-efficient whiteboard tied to the coding session
- Ship with a bundled skill that teaches the agent when a drawing helps
- When to use it
- Useful when you want a coding agent to sketch architecture, flows or quick diagrams while you work, and to react to your own edits on the same board. Best for desktop agent setups rather than web chats.
- Requirements
- Runs as a local process over stdio, installed with npx from the npm package; needs Node.js and a desktop MCP client such as Claude Code, Codex CLI, Gemini CLI, Cursor, Claude Desktop, Windsurf, VS Code or OpenCode. No authentication, environment variables or headers are declared.
Installation
In SourceWeft
- Open Whiteboard MCP in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
https://github.com/user-attachments/assets/197876d8-5620-4c1b-9bc3-332e0e7d5622
Whiteboard MCP is a free and extremely token-efficient whiteboard MCP that runs locally. Your coding agent draws diagrams on a live board beside the chat, and sees what you draw back.
One command install for every agent ↓
Features
[Why Whiteboard MCP: draws step by step, sees what you draw, right beside the chat, remembers boards, local and private, tiny (one runtime dependency, about 7 KB of tool schema per turn).]What you can do with it
Understand an architecture
[An agent chat beside a live whiteboard: the agent draws a checkout architecture step by step, the human drags Postgres, circles the queue and sends a note asking what happens if the email worker is down, and the agent reads the changes and adds a dead-letter queue]Explain a flow
[The agent draws a login flow step by step, highlights the parts it explains, then answers a note left by the human]Play games
[Playing Dots and Boxes with a coding agent: the human draws a line on the board, the agent sees the move and plays back, until red wins 12 to 4]Make something
[An agent paints the Mona Lisa on the board, then refines the sky, hair and dress with pencil strokes]Quick start
[Get started in a minute: 1. Add it to your agent with one npx line. 2. Start a new chat. 3. Ask for a drawing.]Add it to your agent
Cursor, Claude Desktop, Windsurf and other JSON configs (~/.cursor/mcp.json, Claude Desktop's config, …):
OpenCode (opencode.json):
Agents without MCP, project-level configs and more: client setup. The bundled skill teaches the agent when a drawing helps.
Whiteboard MCP vs Excalidraw MCP
[Whiteboard MCP vs Excalidraw MCP: Whiteboard MCP sees what you draw back as a short list of changes, screenshots its own board, edits one shape in place, keeps boards beyond the chat, works in any MCP client plus a CLI, and converts Mermaid. Excalidraw MCP has animated camera moves and zero install.]Want a quick one-off diagram inside Claude or ChatGPT on the web? Excalidraw MCP is great for that. Full comparison →
Client setup · Boards · IDE panel · Tools & how it works · Configuration · Security · Contributing
MIT License · built on Excalidraw
Source: README.md at commit 2444138
Tools
0Version history
6- v0.3.5LatestOct 31, 2026
- v0.3.4Oct 30, 2026
- v0.3.2Oct 30, 2026
- v0.3.0Oct 29, 2026
- v0.2.0Oct 26, 2026
- v0.1.1Oct 23, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts