Liveblocks (Collaborative) MCP Server with 19 Tools for Claude, Cursor, and AI Agents
Manage real-time collaborative rooms, user presence, and shared storage via Liveblocks — list rooms, track active users, and handle threads directly from your AI agent. Vinkius routes your AI agents directly to Liveblocks (Collaborative) through a governed connection. 19 tools ready to use with Claude, ChatGPT, Cursor, or any AI agent — no hosting, no setup, connect in 30 seconds.
Ask AI about this server
Compatible with every major AI agent and IDE

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
What is the Liveblocks MCP Server?
The Liveblocks MCP Server routes AI agents like Claude, ChatGPT, and Cursor directly to Liveblocks via 19 tools. Manage real-time collaborative rooms, user presence, and shared storage via Liveblocks — list rooms, track active users, and handle threads directly from your AI agent. Powered by Vinkius — your credentials stay on your side of the connection, every request is auditable. Connect in under 2 minutes.
Built-in capabilities (19)
Tools for your AI Agents to operate Liveblocks
Ask your AI agent "List all Liveblocks rooms created after January 1st with the metadata 'status:active'." and get the answer without opening a single dashboard. With 19 tools connected to real Liveblocks data, your agents reason over live information, cross-reference it with other MCP servers, and deliver insights you would spend hours assembling manually.
Works with Claude, ChatGPT, Cursor, and any MCP-compatible client. Powered by Vinkius — your credentials never touch the AI model, every request is auditable. Connect in under two minutes.
Why teams choose Vinkius
One subscription gives you the infrastructure to connect your AI agents to thousands of MCP servers — and deploy your own to the Vinkius Edge. Your credentials stay yours. Your data flows directly between your agent and the API. DLP blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade routing and governance, zero maintenance.
Build your own MCP Server with our secure development framework →The Liveblocks (Collaborative) App Connector works with every AI agent you already use
…and any MCP-compatible client


















Use all 19 Liveblocks (Collaborative) tools with your AI agents right now
Vinkius routes your AI agents to Liveblocks (Collaborative) through a governed proxy. Beyond a simple connection, you get full visibility into every action your agents perform, with enterprise-grade security and up to 60% savings on AI costs.
Authorize user on Liveblocks (Collaborative)
Obtain an access token with specific permissions
Broadcast event on Liveblocks (Collaborative)
Broadcast a JSON event to a room
Create room on Liveblocks (Collaborative)
Create a new room
Create thread on Liveblocks (Collaborative)
Create a thread and the first comment
Delete room on Liveblocks (Collaborative)
Delete a room
Get room on Liveblocks (Collaborative)
Retrieve room details
Get storage on Liveblocks (Collaborative)
Get the room's Storage tree (LSON or JSON format)
Get ydoc on Liveblocks (Collaborative)
Get a JSON representation of the Yjs document
Identify user on Liveblocks (Collaborative)
Obtain an ID token for a user
Initialize storage on Liveblocks (Collaborative)
Initialize or reinitialize Storage
List active users on Liveblocks (Collaborative)
List users currently in the room
List rooms on Liveblocks (Collaborative)
List rooms with filtering and pagination
List threads on Liveblocks (Collaborative)
List threads in a room
List versions on Liveblocks (Collaborative)
List Yjs version history snapshots
Patch storage on Liveblocks (Collaborative)
Apply JSON Patch operations to Storage
Resolve thread on Liveblocks (Collaborative)
Resolve a thread
Set presence on Liveblocks (Collaborative)
Set ephemeral presence for a user/agent
Update room on Liveblocks (Collaborative)
Update room properties (metadata, permissions)
Update ydoc on Liveblocks (Collaborative)
Send a binary Yjs update
What the Liveblocks (Collaborative) MCP Server unlocks
Connect your Liveblocks account to any AI agent to orchestrate real-time collaborative experiences and manage infrastructure through natural conversation.
What you can do
- Room Lifecycle — Create, list, update, and delete collaborative rooms with custom metadata and access controls.
- Presence & Interaction — Monitor active users in any room, set ephemeral presence, and broadcast custom events to connected clients.
- Data Synchronization — Retrieve and patch room storage or Yjs documents to manage shared state across collaborative sessions.
- Comments & Feedback — Manage collaborative threads, create new discussions, and resolve existing ones to streamline team feedback.
- User Identity — Authorize and identify users with specific permissions and group assignments via secure token generation.
How it works
1. Subscribe to this server
2. Enter your Liveblocks Secret Key from the dashboard
3. Start managing your real-time infrastructure from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Product Managers — Monitor active collaboration sessions and review user feedback threads without leaving the chat interface.
- Full-stack Developers — Debug room storage, inspect Yjs document states, and manage room permissions directly from the IDE.
- Support Teams — Quickly identify active users in a room and verify room configurations to assist customers in real-time.
Frequently asked questions about the Liveblocks (Collaborative) MCP Server
How can I see which users are currently active in a specific collaboration room?
You can use the list_active_users tool by providing the Room ID. The agent will return a list of all users currently connected to that room, including their connection IDs and associated info.
Is it possible to inspect or modify the shared state of a room from the AI?
Yes! Use get_storage to retrieve the current LSON/JSON storage tree or patch_storage to update specific keys in the room's shared state. For Yjs-based rooms, you can use get_ydoc and update_ydoc.
Can I manage user comments and discussion threads through this integration?
Absolutely. You can use list_threads to see all discussions in a room, create_thread to start a new one, and resolve_thread to mark a discussion as completed.
More in this category

NFe.io
10 toolsOrchestrate NFe.io services — manage service invoices (NFS-e), validate city codes, and monitor company data directly from any AI agent.

Teyuto
10 toolsBuild your own video streaming platform with monetization, audience analytics, and content management for video creators.

7shifts
6 toolsRestaurant workforce management — manage employee schedules, time-off, and staff profiles via AI.

SemVer Version Manager
2 toolsStop LLMs from guessing software versions. Deterministically evaluate semantic version bounds, compatibilities, and sort releases perfectly.
You might also like

Conductor (Netflix OSS)
49 toolsAutomate workflow orchestration via Netflix Conductor — manage workflow and task definitions, and start executions directly from any AI agent.

Gorgias
12 toolsManage your customer support tickets, messages, and user profiles via AI.

EBI PDBe
16 toolsExplore 3D protein structures, ligand interactions, and molecular assemblies from the Protein Data Bank in Europe.

Kontak
10 toolsManage communications — list messages, send SMS, and audit contacts.
We built the connector to Liveblocks (Collaborative). Now put your agents to work. Fully governed.
Vinkius is the AI Gateway with managed hosting. Stop building connectors. Every connection runs inside eight layers of security.
Hosted, sandboxed, and live on AWS. You don't provision anything. You don't maintain anything. You connect.
Every tool call, every token, every response. Logged and auditable. Data flows direct from Liveblocks (Collaborative) to your agent. Nothing is stored on our side. Ever.
Eight governance layers on every request. Sensitive data redacted before it reaches the model. Kill switch if anything goes sideways. Always on.
