How to Use the Liveblocks MCP in Mastra AI

Q: How do I secure Liveblocks access for Mastra AI agents?

Configure your agent with an auth provider. The authorizeuser tool then generates the necessary credentials for each agent session.

Q: Does Mastra AI support human-in-the-loop with Liveblocks?

Yes. Use the requireToolApproval flag on your MCP client. This forces the agent to pause before calling sensitive tools like deleteroom.

Automate collaborative workflows in Mastra AI. Use Liveblocks to manage state across your complex agent pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Liveblocks MCP to Mastra AI

Create your Vinkius account to connect Liveblocks to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Liveblocks with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Mastra AI agent room orchestration

Build agentic workflows that create and manage shared spaces. Your agents use `create_room` and `update_room` to set up environments for multi-step tasks. It removes the need for manual setup. Your Mastra AI agents handle the room lifecycle based on your defined logic.

State persistence in Mastra AI workflows

Keep track of collaborative objects across long-running processes. Agents call `get_storage` to read current state and `patch_storage` to apply updates as the workflow progresses. This ensures your agents always work from the latest version of the data. No more state drift between pipeline steps.

Event-driven collaboration for Mastra AI

Trigger actions based on live room activity. Agents monitor rooms via `list_active_users` and use `broadcast_event` to signal other participants or agents. This adds a layer of coordination to your automated tasks. Your agents respond to changes in real-time as they occur.

Setup guide

Set up Liveblocks MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Liveblocks tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "liveblocks-mcp-client",
  servers: {
    "liveblocks-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Liveblocks Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Liveblocks tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Liveblocks transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Liveblocks. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Liveblocks now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Liveblocks MCP in Mastra AI

Mastra AI supports built-in retry logic. If an MCP call fails, the agent automatically retries based on your workflow configuration.

Absolutely. You can branch your workflow based on the output of `get_room` or `list_threads`. This lets your agents make decisions based on live collaboration state.

Configure your agent with an auth provider. The `authorize_user` tool then generates the necessary credentials for each agent session.

Yes. Use the `requireToolApproval` flag on your MCP client. This forces the agent to pause before calling sensitive tools like `delete_room`.

We isolate your collaborative state within room-specific sandboxes. Every access attempt requires a valid token generated by `authorize_user` for that specific agent.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript