mcpField
L
Liveblocks Mcp Server

Liveblocks Mcp Server

Local
liveblocks.ioDeveloper Tools19Updated 24w ago
RepositoryVisit website

About Liveblocks Mcp Server

The Liveblocks MCP server exposes functions from the Liveblocks REST API so AI can manage rooms, threads, comments and notifications. It also offers read access to Storage and Yjs data. It suits teams building real-time collaboration features with Liveblocks.

Key features

  1. 01Manage rooms, threads, comments and notifications
  2. 02Read-only access to Storage and Yjs data
  3. 03Authenticates with a Liveblocks secret key
  4. 04Configurable in several MCP clients

Use cases

  1. 01Let AI create or modify collaboration rooms
  2. 02Inspect threads and comments
  3. 03Review document data stored in Storage or Yjs

MCP support

This project is an MCP server that exposes Liveblocks REST API functions to MCP clients. After setting the LIVEBLOCKS_SECRET_KEY environment variable, it can be used from clients such as Cursor, Claude Code, Claude Desktop and Codex.

#real-time#ai#toolkit#mcp#websockets#collaboration#crdt#comments#yjs#ai-agents#commenting-system#liveblocks#ai-copilot#mcp-server#api-integration

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "liveblocks": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli"
      ]
    }
  }
}
Run commandnpx -y @smithery/cli

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@smithery/cli

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Liveblocks Liveblocks

liveblocks-mcp-server

This MCP server allows AI to use a number of functions from our REST API. For example, it can create, modify, and delete different aspects of Liveblocks such as rooms, threads, comments, notifications, and more. It also has read access to Storage and Yjs. Learn more in our docs.

Setup

To install, copy your Liveblocks secret key from a project in your dashboard and run one of the following commands, replacing sk_xxxxxxxxxxxx with your secret key.

Cursor
Read more

  1. Go to File → Cursor Settings → MCP → Add new server.
  2. Add the following, inserting your secret key:
{
  "mcpServers": {
    "liveblocks": {
      "command": "npx",
      "args": ["-y", "github:liveblocks/liveblocks-mcp-server"],
      "env": {
        "LIVEBLOCKS_SECRET_KEY": "sk_xxxxxxxxxxxx"
      }
    }
  }
}
Claude Code
Read more

Run the following command in the terminal, inserting your secret key:

claude mcp add liveblocks -e LIVEBLOCKS_SECRET_KEY=sk_xxxxxxxxxxxx -- npx -y github:liveblocks/liveblocks-mcp-server
Claude Desktop
Read more

  1. Go to Settings → Developer → Edit Config.

  2. Open the JSON file, claude_desktop_config.json.

  3. Add the following to the JSON, inserting your secret key:

{
  "mcpServers": {
    "liveblocks": {
      "command": "npx",
      "args": ["-y", "github:liveblocks/liveblocks-mcp-server"],
      "env": {
        "LIVEBLOCKS_SECRET_KEY": "sk_xxxxxxxxxxxx"
      }
    }
  }
}
  1. Restart Claude Desktop to apply the changes.
Codex
Read more

  1. Ensure the Codex CLI is installed:
npm i -g @openai/codex
  1. Run the following command in the terminal, inserting your secret key:
codex mcp add liveblocks \
  --env LIVEBLOCKS_SECRET_KEY=sk_xxxxxxxxxxxx \
  -- npx -y github:liveblocks/liveblocks-mcp-server

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.