mcpField
L
lsp

lsp

Remote
github.com/TagTeamDesignMedia & Design0Updated 34w ago
Repository

About lsp

LightSync Pro connects WordPress sites to MCP clients so AI tools can work with connected creative and commerce assets. The README focuses on endpoint setup, token authentication, and connecting multiple sites.

Key features

  1. 01Streamable HTTP MCP endpoint
  2. 02Token-based site connection
  3. 03Connect multiple WordPress sites
  4. 04SSE endpoint for legacy clients
  5. 05Connection status check

Use cases

  1. 01Configure LightSync Pro in an MCP client
  2. 02Connect separate production and staging sites
  3. 03Use SSE with a client that requires it

MCP support

Provides an MCP endpoint on a WordPress site using Streamable HTTP, with an alternative SSE endpoint for clients that require it. The README gives configuration guidance for Claude.ai, Claude Desktop, Cursor, and Windsurf.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://lightsyncpro.com/connect
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Configuration Examples

Ready-to-use config snippets for connecting LightSync Pro MCP to your AI client.

Replace YOUR_TOKEN with the token from your LightSync Pro plugin settings under AI & Tools → MCP Settings.

Claude.ai (Connector URL)

In Claude.ai settings → Integrations → Add MCP Server:

https://yoursite.com/wp-json/lsp-client/v1/mcp?token=YOUR_TOKEN

This uses the Streamable HTTP transport — no additional setup required.

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "lightsync-pro": {
      "type": "url",
      "url": "https://yoursite.com/wp-json/lsp-client/v1/mcp?token=YOUR_TOKEN"
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project root, or to the global config at ~/.cursor/mcp.json:

{
  "mcpServers": {
    "lightsync-pro": {
      "type": "url",
      "url": "https://yoursite.com/wp-json/lsp-client/v1/mcp?token=YOUR_TOKEN"
    }
  }
}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "lightsync-pro": {
      "type": "url",
      "url": "https://yoursite.com/wp-json/lsp-client/v1/mcp?token=YOUR_TOKEN"
    }
  }
}

Multiple Sites

You can connect multiple WordPress sites simultaneously. Each needs its own token:

{
  "mcpServers": {
    "lightsync-main": {
      "type": "url",
      "url": "https://yoursite.com/wp-json/lsp-client/v1/mcp?token=TOKEN_1"
    },
    "lightsync-staging": {
      "type": "url",
      "url": "https://staging.yoursite.com/wp-json/lsp-client/v1/mcp?token=TOKEN_2"
    }
  }
}

Note: Claude.ai currently deduplicates servers with identical tool names. If connecting multiple sites in Claude.ai, this is a known limitation — the workaround is to use one site at a time via the connector URL.

Verifying the Connection

After configuring, ask your AI client:

"Check my LightSync Pro connection status"

A successful response looks like:

{
  "site_url": "https://yoursite.com",
  "plan": "pro",
  "connected": ["lightroom", "dropbox", "figma"]
}

If you get a 404, verify the plugin is active on your WordPress site and the token matches what's in the plugin settings.

SSE Legacy Transport (Advanced)

For clients that require the SSE transport instead of Streamable HTTP:

https://yoursite.com/wp-json/lsp-client/v1/mcp/sse?token=YOUR_TOKEN

The SSE endpoint supports both GET (stream) and POST (message). Most modern clients should use the standard /mcp endpoint above.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.