Draw2agent MCP server
io.github.zero-abd/draw2agent·v1.3.4·3 starsDraw on your website, let your AI agent see it. Visual context for code generation via MCP.
3 stars32 downloads/wk
Reviews
Write oneNobody has reviewed Draw2agent yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Draw2agent tools (1)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
launch_canvasLaunch a browser canvas overlay on top of the user's local development page. The user can draw annotations (circles, arrows, text) directly on their website, then submit to capture a screenshot and DOM context for the agent. This tool will block and wait until the user has submitted their drawings, returning the full visual context.
Public scan report
scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it
- Code scan4 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 134 days ago8/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Draw2agent compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 82/100
- higher than 65% of 4,460 AI and agents servers
- Tools
- 1
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 3
- more than 75% of 2,711 AI and agents servers
- Downloads a week
- 32
- more than 20% of 1,538 AI and agents servers with a package
What its tools let an agent do: 1 read
Install Draw2agent in Claude Code, Cursor or VS Code
Runs npx -y draw2agent on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add draw2agent -- npx -y draw2agent
What the publisher says
From the Draw2agent repository's README, as published. We do not edit it. Read it on GitHub
draw2agent ✏️
Draw on your website. Your AI agent sees it.
draw2agent is an MCP server that lets you draw annotations directly on top of your local dev page. When you submit, your IDE agent receives a screenshot, structured DOM data, and annotation context to make precise code edits.
👉 Try it out at: draw2agent.vercel.app
Demo
Quick Start
1. Add to your IDE (one-time)
Cursor (~/.cursor/mcp.json):
{
"mcpServers": {
"draw2agent": {
"command": "npx",
"args": ["-y", "draw2agent@latest"]
}
}
}2. Use it
Tell your agent:
"Use draw2agent to fix the navbar"
- 🌐 Agent opens your browser with drawing tools on your page
- ✏️ Draw circles, arrows, text directly on your website
- 📸 Click Submit
- 🤖 Agent reads the visual context and applies code changes
How It Works
Your Dev Page (proxied)
├── Your original page content
└── Excalidraw overlay (transparent, on top)
├── Draw mode: annotate directly on the page
├── Select mode: interact with the page normally (Esc)
└── Submit: screenshot + DOM + annotations → agentTools
The MCP server exposes the following tools:
launch_canvas
The core tool — proxies your localhost dev server and injects an Excalidraw overlay. Draw annotations directly on your running app, then submit to send visual context to your agent. The tool blocks until you submit.
launchipadcanvas
Same as launchcanvas, but serves the proxy on your computer's local network (LAN) address. Automatically opens a new browser tab on your computer with a QR code. Scan it from your iPad or phone — connected to the same Wi-Fi network** — to draw annotations with touch. Perfect for whiteboard-style feedback sessions. No internet tunnel required, so it's fast and reliable.
launch_scratch
Opens a blank Excalidraw whiteboard — no target URL needed. Sketch UI mockups, wireframes, or diagrams from scratch. Your agent receives the drawing and implements the design.
getdrawingstate
Returns the last captured drawing state (screenshot, DOM nodes, annotations) without launching a new session. Useful for re-fetching context.
Releasing
Publishing to npm is automated via GitHub Actions (.github/workflows/publish.yml). To cut a release, just bump the version and push to main:
npm version patch # or minor / major — updates package.json
git push origin mainWhen package.json's version changes on main, the workflow builds the server + overlay and publishes the new version to npm. You can also trigger it manually from the Actions tab (e.g. to publish the current version).
One-time setup: npm Trusted Publishing
The workflow authenticates with npm via OIDC — no NPMTOKEN secret needed**. Configure the trusted publisher once:
- Go to npmjs.com/package/draw2agent → Settings → Trusted Publisher.
- Choose GitHub Actions and enter:
- Organization or user: zero-abd
- Repository: draw2agent
- Workflow filename: publish.yml
- Save.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Draw2agent: common questions
- Is Draw2agent MCP server safe?
- Mostly: it is graded B (82/100). Read the Draw2agent safety report
- How do I install Draw2agent?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Draw2agent need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Draw2agent maintained?
- The last commit was 171 days ago (2026-05-17). The latest release is v1.3.4.
- What can I use instead of Draw2agent?
- Servers from other publishers that do the same job: Agent-Native Plan MCP server, Image MCP server and Openflowkit MCP server.
- How does Draw2agent compare with other AI and agents MCP servers?
- safety score 82/100 (higher than 65% of 4,460 AI and agents servers); tools 1 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Draw2agent
Same job from other publishers: the closest match first, then the best rated.
- Agent-Native PlanStructured visual plans and PR recaps with diagrams, prototypes, annotations, and sharingnot reviewedEstablishedA
- ImageAI image generation and editing with prompt optimization and quality presetsnot reviewedEstablishedB
- OpenflowkitArchitecture diagrams for your agent: draw on the live OpenFlowKit canvas or edit diagram files.not reviewedEstablishedA