Web Whiteboard

A web-based whiteboard for displaying output from Chatbots and LLMs.

A Web-based Whiteboard with MCP interface

whiteboard-mcp is a simple whiteboard web application, providing a convenient way for displaying Chatbot/LLM's output.

- Web whiteboard— Browser UI to show content pushed by agents or other clients; good for demos and side-by-side LLM output.
- Any screen— Open the board URL in a browser on any monitor, projector, or device on your network.
- Dual MCP transports—Streamable HTTPat/mcpandSSEat/ssefor clients that only support one style.
- REST API—GET/POST /api/contentfor non-MCP integrations; history list/restore/delete under/api/history.
- History— Server-side history of updates; reopen a past version from the history UI (and via the history API).
- Export— Save the current view asHTMLorMarkdownfrom the menu;Print / PDF(browser print-to-PDF) when the board shows HTML or Markdown.
- Bilingual UI— English and Chinese interface, file or in-app settings.

pip install whiteboard-mcp # or: # uv tool install whiteboard-mcp whiteboard-mcp

git clone .../whiteboard-mcp cd whiteboard-mcp uv run whiteboard_mcp

The server listens on0.0.0.0:5000by default.

Use your machine's LAN IP instead of127.0.0.1when connecting from another device on the same network.

The MCP server exposes these tools (names as registered with clients):

Clients that supportStreamable HTTPnatively should point their MCP server URL athttp://127.0.0.1:5000/mcp(adjust host/port for LAN as needed).

Add an HTTP transport entry undermcp_serversin~/.hermes/config.yaml, then restart Hermes. Example:

mcp_servers: whiteboard: url: "http://127.0.0.1:5000/mcp"

For example you can use mcp-remote to connect /sse API:

{ "mcpServers": { "whiteboard-mcp": { "command": "npx", "args": [ "mcp-remote", "http://127.0.0.1:5000/sse", "--allow-http" ] } } }

Collaborative word processor you can use with your agent

Carryo is a remote MCP server for sharing Claude or ChatGPT-created HTML artifacts as live links.

An MCP server that enables AI assistants to interact with Confluence content through a standardized interface.

Publish Markdown or HTML to a clean, shareable link straight from your AI assistant — OAuth, no API keys.

An MCP server for interacting with the esa.io knowledge-sharing platform.

Access the esa.io API to manage your team's knowledge base.

A MCP server for the document sharing service esa.io.

A Model Context Protocol (MCP) server for integrating Google Docs with AI clients.

Create, edit, inspect, and publish collaborative HTML documents from AI agents.

A secure, multi-user server connecting LLMs to Microsoft 365 services.