docs/integrations/claude-desktop

How to connect the Web Crawl & Page Extractor MCP Tool to Claude Desktop

Fetches any URL and returns structured page content (metadata, headings, links) without browser automation. This guide provides the exact configuration required to load the agentic_web_crawl tool inside Claude Desktop.

Step 1: Open the configuration file

Locate and open your Claude Desktop configuration file at the following path:

macOS / Linux~/Library/Application Support/Claude/claude_desktop_config.json

Windows%APPDATA%\Claude\claude_desktop_config.json

Step 2: Add the server config

Copy and paste the following JSON snippet into the file. Save the file and restart Claude Desktop.

claude_desktop_config.json

{
  "mcpServers": {
    "agenticstore": {
      "command": "uvx",
      "args": ["agentic-store-mcp", "--tools", "agentic_web_crawl"]
    }
  }
}

Step 3: Try it out

Once restarted, ask Claude Desktop something like this to trigger the tool:

"Crawl https://example.com and summarize the main content."

Explore more

→ View full agentic_web_crawl documentation → See all Client integrations