liveblocks
MCP server for Liveblocks.
claude mcp add --transport stdio liveblocks-liveblocks-mcp-server node /full/path/to/the/repo/liveblocks-mcp-server/build/index.js \ --env LIVEBLOCKS_SECRET_KEY="<your-liveblocks-secret-key>"
How to use
This MCP server exposes a set of Liveblocks REST API capabilities to be used by your AI workflows. It provides operations to manage Liveblocks resources such as rooms, threads, comments, and notifications, and it can also read from Storage and Yjs when needed. With the server running, you can leverage the included MCP endpoints to automate tasks like creating or updating rooms, posting messages, or querying data from Liveblocks, all within your AI agent prompts and workflows. To interact with it, start the Node.js server and configure your MCP client to point at the server’s index.js entrypoint, supplying your Liveblocks secret key via environment variables. The server is designed to be invoked by MCP clients through the standard mcpServers configuration and will respond with the appropriate Liveblocks API results for the requested actions.
How to install
Prerequisites:
- Node.js and npm installed on your machine (or the target environment).
- Access to a Liveblocks secret key from your Liveblocks dashboard.
Manual setup steps:
-
Clone the repository git clone https://github.com/liveblocks/liveblocks-mcp-server.git
-
Install dependencies and build npm install npm run build
-
Obtain your Liveblocks secret key from the Liveblocks dashboard.
-
Register the MCP server in your client (example for Cursor): Place the following configuration in the MCP settings, replacing the placeholder path with your actual repo path and key:
{ "mcpServers": { "liveblocks-mcp-server": { "command": "node", "args": ["/full/path/to/the/repo/liveblocks-mcp-server/build/index.js"], "env": { "LIVEBLOCKS_SECRET_KEY": "<your-liveblocks-secret-key>" } } } }
-
Start using the MCP server by ensuring the configuration is enabled in the MCP menu of your client.
Additional notes
Tips and caveats:
- Ensure the LIVEBLOCKS_SECRET_KEY environment variable is kept secret and not exposed in logs or shared configurations.
- The server exposes REST API capabilities via the Liveblocks integration; consult the Liveblocks docs for endpoint specifics and rate limits.
- If you rotate your secret key, update the MCP configuration accordingly and restart the server.
- For Claude Desktop or other clients, you may need to adapt the JSON config to your client’s config schema (the liveblocks-mcp-server example shows typical usage).
- When deploying in production, consider securing your environment (e.g., using secrets management) and limiting access to trusted clients.
- If you run into build steps, ensure npm install completes successfully and that the build output exists at build/index.js as referenced in the config.
Related MCP Servers
ai-trader
Backtrader-powered backtesting framework for algorithmic trading, featuring 20+ strategies, multi-market support, CLI tools, and an integrated MCP server for professional traders.
robloxstudio
Create agentic AI workflows in ROBLOX Studio
mcp
🤖 Taskade MCP · Official MCP server and OpenAPI to MCP codegen. Build AI agent tools from any OpenAPI API and connect to Claude, Cursor, and more.
mcpcat-python-sdk
MCPcat is an analytics platform for MCP server owners 🐱.
mcp -js
MCP server that exposes YepCode processes as callable tools for AI platforms. Securely connect AI assistants to your YepCode workflows, APIs, and automations.
packt-netops-ai-workshop
🔧 Build Intelligent Networks with AI