PromptBoard
A shared whiteboard server that enables users to provide visual context to AI agents by pasting screenshots and drawing annotations. It allows agents to analyze images, sketches, and marked-up details directly through the Model Context Protocol.
README
đ¨ PromptBoard
The Shared Whiteboard for AI Agents via MCP.
Paste screenshots, highlight specific details, and share visual context directly via MCP. Stop saving images to files. Just copy, paste, mark, and ask.
Demo:
https://github.com/user-attachments/assets/3a07ca9d-d989-4d6c-aef1-4eebbd6d0cca
đ Quick Start
Standard Configuration
Add to your MCP client configuration:
{
"mcpServers": {
"promptboard": {
"command": "npx",
"args": ["-y", "promptboard"]
}
}
}
<details> <summary><b>Claude Desktop</b></summary>
Config Location:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Configuration:
{
"mcpServers": {
"promptboard": {
"command": "npx",
"args": ["-y", "promptboard"]
}
}
}
Restart Claude Desktop and test:
- "Open the whiteboard"
- "What's on the whiteboard?"
</details>
<details> <summary><b>Claude Code</b></summary>
claude mcp add promptboard "npx -y promptboard"
Custom Commands (Optional):
npx promptboard init claude-code
This creates .claude/commands/:
/whiteboard- Opens the visual whiteboard/check-board [message]- Analyzes whiteboard content
Example:
/check-board What does the red section mean?
</details>
<details> <summary><b>Gemini CLI</b></summary>
Config Location: .gemini/settings.json in your project
Configuration:
{
"mcpServers": {
"promptboard": {
"command": "npx",
"args": ["-y", "promptboard"]
}
}
}
Custom Commands (Optional):
npx promptboard init gemini-cli
This creates .gemini/commands/:
/whiteboard- Opens the visual whiteboard/check-board [message]- Analyzes whiteboard content
</details>
For detailed installation instructions, including manual setup and building from source, please refer to the MCP Setup Guide.
Features
- đ¨ Whiteboard Canvas - Draw, sketch, and annotate freely
- đ¸ Screenshot Support - Paste images directly with
Ctrl+V - đī¸ Drawing Tools - Pen, shapes, text, eraser
- âŠī¸ Undo/Redo - Full history management (
Ctrl+Z,Ctrl+Shift+Z) - đ Multi-language - English, Korean, Japanese
- đ Dark/Light Theme - Customizable appearance
- đ¤ AI Integration - MCP protocol for Claude Code, Gemini CLI
- đž Auto-save - Persistent state across sessions
Documentation
User Guides
- MCP Setup Guide - Installation and configuration
- MCP Architecture - Internal architecture details
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.