1. Home
  2. Fetcher MCP
  3. Fetcher MCP for Claude Desktop: Setup & Config

Data as of

Fetcher MCP for Claude Desktop: Setup & Config

Claude Desktop: Fetcher MCP retrieves web pages through Playwright and returns their content as Markdown or HTML.

What you can do with Fetcher in Claude Desktop

Pick it for browser-rendered content extraction with parallel fetching and practical debugging controls.

  • Read content from JavaScript-rendered web pages.
  • Extract article text without navigation and ads.

Before you start: Fetcher in Claude Desktop

  • Node.js and npx
  • Playwright Chromium
  • An MCP-compatible client

The README first installs the browser with npx playwright install chromium. The browser_install tool can also resolve missing-browser errors. An HTTP launch alternative exposes /mcp and /sse. No required environment variables are stated.

Fetcher Claude Desktop configuration

  1. Choose Claude Desktop configuration scope

    For Fetcher MCP, open macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json. Merge under mcpServers via Settings → Developer → Edit Config when available.

  2. Add Fetcher MCP to Claude Desktop

    Use the fetcher-mcp entry below in mcpServers. Keep Fetcher MCP's documented stdio connection fields and your other Claude Desktop entries.

  3. Check Fetcher MCP in Claude Desktop

    Fetcher MCP: Fully quit and reopen Claude Desktop; check developer diagnostics.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

JSON
{
  "mcpServers": {
    "fetcher-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "fetcher-mcp"
      ],
      "env": {}
    }
  }
}

Fetcher tools available to Claude Desktop

Fetcher's stored tool list documents 3 tools; compare it with Claude Desktop's connected tool list, because the stored list is not a live check.

fetch_url

When Claude Desktop requests fetch_url from Fetcher, review the action before approving it.

Load one URL in Playwright and return extracted or full page content.

fetch_urls

When Claude Desktop requests fetch_urls from Fetcher, review the action before approving it.

Retrieve several URLs concurrently with the same content and loading controls.

browser_install

When Claude Desktop requests browser_install from Fetcher, review the action before approving it.

Fetcher: full stored tool descriptions

Troubleshooting Fetcher in Claude Desktop

  • Fully quit and reopen Claude Desktop for Fetcher MCP. If npx fetcher-mcp (Node.js/npm) is missing, check the desktop process's PATH, which may differ from your terminal.
  • Fetcher MCP uses stdio here: Claude Desktop must keep the configured process running; protocol output belongs on stdout and diagnostics on stderr.
  • Known limitation: Needs a Playwright Chromium binary and associated runtime dependencies.
  • Known limitation: Verification-heavy pages may require manual interaction or timeout tuning.
  • Known limitation: Default resource blocking changes what the browser loads.
  • General Claude Desktop troubleshooting lives in the /clients/claude-desktop guide.

Fetcher MCP — details. Claude Desktop guide

Frequently asked questions

Claude Desktop loads Fetcher MCP from claude_desktop_config.json: ~/Library/Application Support/Claude/ on macOS, or %APPDATA%\Claude\ on Windows. Open it via Settings → Developer → Edit Config when available.

Claude Desktop's fetcher-mcp example uses stdio.

Fetcher MCP's Claude Desktop configuration invokes npx fetcher-mcp (Node.js/npm).

Fetcher MCP's stored list contains 3 tools, including fetch_url, fetch_urls, browser_install. Compare those names with Claude Desktop's connected tool list; the stored list is not a live check.

Yes. It loads pages using Playwright and executes their JavaScript before collecting content.

Yes. Enable returnHtml; disabling extractContent also retains content beyond the extracted main section.