Connect Manycrawl to Claude

Step 1Open the app and sign in

The desktop app is the engine, so it has to be running. Opening it also starts the local bridge on port 8765 and the scraper sidecar on 8766 — you do not run those yourself, and you do not need Node installed. The app ships its own.

If you have logged into Apollo, Facebook or LinkedIn in its built-in browser, those sources are available to the agent too.

Step 2Click Connect Claude Desktop

In the app: Settings → Connect Claude Desktop → Connect. The badge turns to Connected.

That one click adds a manycrawl server to your Claude config at ~/.claude.json, pointing at the bridge the app is already running:

{
  "mcpServers": {
    "manycrawl": { "type": "http", "url": "http://127.0.0.1:8765/mcp" }
  }
}

It merges into the file rather than replacing it, backs up what was there first, and touches only the manycrawl key. Disconnect on the same card takes it back out. If Claude Desktop was already open, restart it.

Step 3Ask for a list in the Code tab

Open the Code tab in Claude Desktop, approve the tools once, then ask. Say the word Manycrawl in the request:

"Use Manycrawl to find 50 dentists in Ljubljana and get their emails."

Naming it matters. Without it Claude may answer from a web search instead — which returns names but rarely phone numbers or emails, and leaves no table behind in the app.

CheckIs it working?

Ask Claude to call manycrawl_engine_status. A healthy answer looks like this:

{
  "bridge": true,
  "dashboardAlive": true,
  "engine": { "desktop": true, "authenticated": true, "isPro": true }
}

Leave the app running and signed in while you work. You do not have to keep the window in front of you — closing it hides the app to the tray and it keeps serving. Quitting it properly stops the bridge, and Claude loses the server until you open the app again.

DevRunning from source

Only if you are working from a checkout of the repo rather than the installed app. Here you do need Node, and you start the bridge yourself:

cd claude-code-bridge
npm install
node bridge-server.js

Then add the entry to your MCP config by hand — the same HTTP form the button writes:

{
  "mcpServers": {
    "manycrawl": { "type": "http", "url": "http://127.0.0.1:8765/mcp" }
  }
}

Or, if you would rather Claude spawn the server itself over stdio, point it at the script with an absolute path:

{
  "mcpServers": {
    "manycrawl": {
      "command": "node",
      "args": ["/path/to/claude-code-bridge/mcp-server.mjs"]
    }
  }
}

Configure one or the other, never both — they expose the same tools twice. And do not run a hand-started bridge alongside the installed app: the app claims port 8765 on launch and will stop whatever else is holding it.