How to Use the Liveblocks MCP in CrewAI

Q: How do agents track state changes in Liveblocks and CrewAI?

Agents poll the storage state using getstorage. When a change is detected, the agent updates its internal context accordingly.

Coordinate your CrewAI agents with Liveblocks. Enable shared memory and collaborative state for specialized agent teams.

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 CrewAI

Create your Vinkius account to connect Liveblocks to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Shared memory for CrewAI agent teams

Give your agents a common place to store and retrieve information. Agents use `get_ydoc` and `update_ydoc` to keep their internal knowledge synced. This allows specialized agents to see exactly what their teammates are working on. It creates a unified workspace for the entire crew.

Thread management for CrewAI crews

Enable asynchronous communication between agents and human supervisors. Agents use `list_threads` and `resolve_thread` to manage feedback loops. This keeps your operations organized. Your agents track their progress and flag issues for human review in the same threads.

Agent-led room administration in CrewAI

Automate the housekeeping of your collaborative environments. Agents call `list_rooms` to find active work and `delete_room` to clean up when tasks finish. This keeps your infrastructure lean. Your crew manages its own resources without human intervention.

Setup guide

Set up Liveblocks MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Liveblocks tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Liveblocks Analyst",
    goal="Access and analyze Liveblocks data via MCP.",
    backstory="Expert analyst with direct Liveblocks access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Liveblocks transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Liveblocks Analyst",
        goal="Access and analyze Liveblocks data via MCP.",
        backstory="Expert analyst with direct Liveblocks access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Liveblocks transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Yes. By sharing a room ID, your agents can read and write to the same storage. This enables real-time synchronization between different crew members.

Pass the server URL to the agent's MCP configuration. This allows the agent to discover and use all 18 available tools.

It does. You can assign different access levels to specific agents. The manager agent can authorize subordinates via `authorize_user`.

Agents poll the storage state using `get_storage`. When a change is detected, the agent updates its internal context accordingly.

We secure your JSON storage and Yjs document structures using per-room authorization tokens. Each agent only sees what you explicitly allow.

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

Mastra AI sdk-typescript

Start using the Liveblocks MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started