sync. labs MCP Server — Use sync. labs from Claude, ChatGPT & AI Assistants via MCP
sync. labs MCP Server — Use sync. labs from Claude, ChatGPT & AI Assistants via MCP
sync. labs MCP Server — Use sync. labs from Claude, ChatGPT & AI Assistants via MCP
The Sync Labs MCP server is an open-source Model Context Protocol server that connects AI assistants — including Claude Web, ChatGPT, Claude Desktop, Cursor, and Windsurf — to the Sync Labs lipsync API. Instead of writing code or using the Studio, describe what you want in plain English and your AI assistant handles the API calls for you.
The Sync Labs MCP server auto-generates tools from the Sync Labs API spec at startup. As new API endpoints ship, they become available to your AI assistant automatically — no update needed.
The Sync Labs MCP server supports these AI clients, with more being added as the MCP ecosystem grows:
Web clients (OAuth — no installation required):
Local clients (npm package — requires Node.js 18+):
For Claude Web and ChatGPT Web — connect in your browser with zero installation. Authentication is handled via OAuth, so no API key is needed.
The OAuth flow connects to your currently active Sync Labs organization. To switch organizations, disconnect the integration, change your active organization at sync.so, and reconnect.
Sync Labs and URL: https://mcp.sync.so/mcpSync Labs tools will appear in Claude’s tool picker. Try asking: “Create a lipsync video with this video and audio URL.”
Sync Labs, Description: Lipsync videos from any video + audiohttps://mcp.sync.so/mcpOAuthChatGPT MCP apps are currently in beta. You’ll need to check the “I understand and want to continue” box when creating the app.
For desktop apps, CLI tools, and code editors. Requires:
Add the following to your claude_desktop_config.json:
Where to find this file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonRestart Claude Desktop after saving.
Add the following to your ChatGPT Desktop MCP config:
Where to find this file:
~/Library/Application Support/com.openai.chat/mcp.json%APPDATA%\com.openai.chat\mcp.jsonRestart ChatGPT Desktop after saving.
Run this one-liner to add Sync Labs to Claude Code:
Or add to .mcp.json in your project root:
Add to .cursor/mcp.json in your project:
Any MCP-compatible client can use the Sync Labs MCP server. The configuration is the same — point it at npx -y @sync.so/mcp-server with your API key set as SYNC_API_KEY in the environment.
See the MCP protocol docs for client-specific setup instructions.
Once connected, you can create lipsync videos, check generation status, estimate costs, and manage assets — all through natural language. Here are example prompts you can try with your AI assistant:
The Sync Labs MCP server exposes all public Sync Labs API endpoints as tools. Core tools include:
The Sync Labs MCP server works with any model available through the API. Asset uploads are not yet available via the API — use publicly accessible URLs for video and audio inputs.
The Sync Labs MCP server is one of three ways to integrate with the Sync Labs API. Choose the approach that best fits your workflow:
The Sync Labs MCP server is ideal when you want to explore the API, prototype workflows, or create lipsync videos without writing code. For production applications, the Sync Labs SDKs or REST API give you full programmatic control.
The Sync Labs MCP server accepts the following options when run directly:
You can also use the Sync Labs MCP server as a library in your own applications. This is useful when you want to embed Sync Labs’ MCP tools into a custom AI agent or multi-tool pipeline:
The Sync Labs MCP server exposes the same auto-generated tools when used programmatically, so your custom agents get access to every public Sync Labs API endpoint.
If you see sh: mcp-server: command not found or similar errors when using the npx configuration, this is typically caused by Node version managers (nvm, fnm, volta) not resolving npx bin paths correctly.
Fix: Install the package globally and reference it directly:
Then update your MCP config to use sync-mcp instead of npx:
If that still doesn’t work, use the full path to node:
No. The Sync Labs MCP server runs via npx, which downloads the package automatically. Node.js 18+ is the only prerequisite. You can also install it globally with npm install -g @sync.so/mcp-server if you prefer.
Yes. The Sync Labs MCP server fetches the latest OpenAPI spec from the Sync Labs API on every startup. When new endpoints are added to the Sync Labs API, they become available as MCP tools automatically — just restart the server.
Yes — if you’re using a web client (Claude Web or ChatGPT Web), authentication is handled via OAuth and no API key is needed. For local clients (desktop apps, CLI tools, and code editors), a Sync Labs API key is required.
The Sync Labs MCP server supports 9 AI clients: Claude Web, ChatGPT Web, Claude Desktop, ChatGPT Desktop, Claude Code, Cursor, Windsurf, Codex CLI, and any MCP-compatible client. See the supported clients table for details.
Asset uploads are not yet available through the Sync Labs API, so they are not available through the Sync Labs MCP server either. Use publicly accessible URLs for your video and audio inputs. Once uploads are added to the Sync Labs API, they will automatically become available through the Sync Labs MCP server.