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.
Automatic setup
To install automatically, copy your Liveblocks secret key from a project in your dashboard and run one of the following commands, replacing [key] with your secret key.
Cursor
npx -y @smithery/cli install @liveblocks/liveblocks-mcp-server --client cursor --key [key]
Claude Desktop
npx -y @smithery/cli install @liveblocks/liveblocks-mcp-server --client claude --key [key]
VS Code
npx -y @smithery/cli install @liveblocks/liveblocks-mcp-server --client vscode --key [key]
Other clients
Find installation information for other clients on Smithery.
Manual setup
Read more
- Clone this repo.
git clone https://github.com/liveblocks/liveblocks-mcp-server.git
- Build the project.
npm install
npm run build
- Get your Liveblocks secret key from the dashboard.
sk_dev_Ns35f5G...
Cursor
-
Go to File → Cursor Settings → MCP → Add new server.
-
Add the following, with the full path to the repo and your secret key:
{
"mcpServers": {
"liveblocks-mcp-server": {
"command": "node",
"args": ["/full/path/to/the/repo/liveblocks-mcp-server/build/index.js"],
"env": {
"LIVEBLOCKS_SECRET_KEY": "sk_dev_Ns35f5G..."
}
}
}
}
- Check it's enabled in the MCP menu.
Claude Desktop
-
Go to File → Settings → Developer → Edit Config.
-
Open the JSON file,
claude_desktop_config.json. -
Add the following, with the full path to the repo and your secret key:
{
"mcpServers": {
"liveblocks-mcp-server": {
"command": "node",
"args": ["/full/path/to/the/repo/liveblocks-mcp-server/build/index.js"],
"env": {
"LIVEBLOCKS_SECRET_KEY": "sk_dev_Ns35f5G..."
}
}
}
}
Recommend MCP Servers 💡
windows-rs-mcp
MCP server for searching Rust windows crate API documentation
mcp-server-google-search
A microservice for Google Custom Search with caching, rate-limiting, metrics, and robust error handling, providing REST and GraphQL endpoints.
searxng-mcp-server
An MCP server implementation integrated with SearXNG for privacy-respecting search capabilities for AI agents.
druid-mcp-server
A comprehensive MCP server for Apache Druid with tools, resources, and AI prompts for cluster management and analysis.
@skeetbuild/opensearch
A Model Context Protocol server providing read-only access to OpenSearch clusters for LLMs to inspect indices and execute queries.
mcp-server-aoai-dalle3
An Azure OpenAI DALL-E 3 integration server implementing the Model Context Protocol (MCP). This server provides a bridge between Azure OpenAI's DALL-E 3 image generation capability and MCP clients.