Overboard Studio MCP Server
Enables AI agents to create and manage collaborative whiteboards with sticky notes, shapes, charts, and more, directly in Overboard Studio.
README
Overboard Studio — MCP Server
Overboard Studio is a collaborative whiteboard. This is the official Model Context Protocol (MCP) server: it lets any AI agent (Claude, ChatGPT, Cursor, Codex, …) create and manage real, shareable boards — sticky notes, shapes, text, frames, charts, flowcharts, tables, connectors — that show up live in the Overboard web app.
Hosted endpoint (recommended): https://overboard.studio/mcp (OAuth, supports Claude.ai, ChatGPT, Cursor, etc.)
Stdio mode: for Claude Code / Cursor / Claude Desktop running locally.
Quick connect
Claude.ai (web)
Settings → Connectors → Add custom connector → URL: https://overboard.studio/mcp → complete the OAuth flow.
Claude Code
claude mcp add --transport http overboard https://overboard.studio/mcp
/mcp auth
Claude Desktop (stdio)
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"overboard": {
"command": "npx",
"args": ["-y", "@overboard/mcp-server"],
"env": {
"SUPABASE_URL": "https://your-project.supabase.co",
"SUPABASE_SERVICE_ROLE_KEY": "your-service-role-key"
}
}
}
}
Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"overboard": {
"url": "https://overboard.studio/mcp"
}
}
}
Tools (16)
Boards
| Tool | Description | Annotation |
|---|---|---|
get_current_user |
Authenticated user's id, email, display name | read-only |
list_boards |
Boards you own or were invited to | read-only |
get_board |
Board metadata + member/element counts | read-only |
create_board |
New empty board, you become owner | write |
create_board_with_elements |
New board pre-populated with elements (preferred) | write |
rename_board |
Rename a board you own | write, idempotent |
delete_board |
Cascade-delete board, members, elements | destructive |
get_board_url |
Direct URL to open board in the web app | read-only |
Elements
| Tool | Description | Annotation |
|---|---|---|
get_elements |
All elements on a board | read-only |
create_element |
Add sticky note / shape / text / frame / chart / etc. | write |
bulk_create_elements |
Batch create (preferred for >2 elements) | write |
update_element |
Merge properties — move/resize/recolor/edit text | write, idempotent |
delete_element |
Remove a single element | destructive |
Collaboration
| Tool | Description | Annotation |
|---|---|---|
get_collaborators |
Members of a board with roles | read-only |
get_board_activity |
Recent element changes (default last 24h) | read-only |
invite_to_board |
Generate a shareable invitation link | write |
Element types
sticky-note, text, path, shape, connector, frame, graph, chart, flowchart, table, timeline, kanban, doc, vote, timer, estimation
Smart defaults are applied for position, size, and styling — you only need to specify what you want to customize.
Authentication
The hosted endpoint uses OAuth 2.0. The client (Claude.ai, etc.) walks the user through Overboard's auth flow once; tokens are valid for 30 days.
Stdio mode uses the Supabase service-role key — pass it as an env var. Each tool call enforces per-user board access via Supabase Row-Level Security; the service-role key only bypasses RLS for the tools that need to read/write multi-user state.
Build from source
npm install
npm run build
node dist/index.js
For HTTP mode:
node dist/index.js --http --port=3002
Test with MCP Inspector
SUPABASE_URL=... SUPABASE_SERVICE_ROLE_KEY=... \
npx @modelcontextprotocol/inspector node dist/index.js
Example prompts
Once connected, try:
- "List all my boards"
- "Create a sprint planning board with 5 yellow sticky notes for: Design login, Set up API, Write tests, Deploy staging, Code review"
- "Show me everything on board {id}"
- "Move the first sticky note to (500, 300) and recolor it green"
- "Generate an invite link for board {id} as editor"
License
MIT
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.