Using LDX hub with AI Assistants (MCP)
LDX hub supports the Model Context Protocol (MCP), which allows you to use StructFlow and RefineLoop directly from AI assistants like Claude Desktop — without writing any code.
Once connected, you can ask your AI assistant to run structured data extraction or translation refinement jobs on your behalf.
Prerequisites
- An LDX hub API key (available after subscribing via this Developer Portal)
- Claude Desktop installed on your machine
- Node.js (v18 or later) installed on your machine
Setup Instructions
Mac
- Open Terminal and navigate to the Claude configuration directory:
Code
- Open or create
claude_desktop_config.jsonand add the following:
Your MCP server URL is your API base URL with /mcp appended.
You can find your API base URL in the API Reference page under SERVERS (top right).
Code
- Save the file and restart Claude Desktop.
Windows
- Open Claude Desktop and go to Settings → Developer.
- Click Edit Config to open the configuration file directly.
- Add the following to the file:
Your MCP server URL is your API base URL with /mcp appended.
You can find your API base URL in the API Reference page under SERVERS (top right).
Code
- Save the file and restart Claude Desktop.
Verification
After restarting Claude Desktop, you should see an MCP icon in the chat interface. You can verify the connection by asking Claude:
"List the available StructFlow models."
If the connection is working, Claude will return the current list of available AI models.
What You Can Do
Once connected, you can ask your AI assistant to:
- List available models for StructFlow or RefineLoop
- Submit a StructFlow job to extract structured data from text
- Submit a RefineLoop job to refine XLIFF translation quality
- Check the status of a running job
- Download completed results
If you have any issues, contact us.