OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
MCP & Tooling

Fetcher MCP

Fetcher MCP is a TypeScript MCP server that uses a Playwright headless browser to retrieve web-page content for compatible clients. It offers single-URL and parallel multi-URL fetching, Readability-based main-content extraction, and Markdown or HTML output.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Fetcher MCP — OpenViST project profile in MCP & Tooling.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Fetcher MCP when an MCP-compatible client needs browser-based page retrieval as an input to a research or content-processing workflow.

Who it is for

  • Developers connecting browser-based web retrieval to MCP-compatible agents or clients.
  • Teams building research workflows that need page content returned in a format suitable for downstream processing.

Documented uses

  • Fetch a web page that depends on JavaScript rendering.
  • Extract a page's main content and return it as Markdown or HTML.
  • Retrieve several URLs concurrently and collect their results.
Before you choose

Requirements & limits

The project repository lists an MIT license. The README documents npx-based setup, a Playwright Chromium installation step, Claude Desktop configuration, HTTP/SSE transport, and Docker deployment.

  • Playwright executes JavaScript, supporting retrieval from dynamic pages.
  • Main-content extraction is enabled by default; HTML output can be selected instead of the default Markdown output.
  • The fetch_urls tool processes multiple URLs concurrently.
  • Images, stylesheets, fonts and media are disabled by default according to the README.
  • The documented setup includes installing the Chromium browser binary.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Fetcher MCP with Claude Desktop

Install the browser prerequisite and add the documented Fetcher MCP server configuration to Claude Desktop.

Before you start

  • Node.js and npx, as used by the documented launch command
  • Playwright Chromium
  • Claude Desktop

Steps

  1. Install Chromium with the command below.

    Documented command
    npx playwright install chromium

  2. Add the README's fetcher server entry, using command npx and arguments -y and fetcher-mcp, to the Claude Desktop MCP configuration file.

  3. Use the documented macOS or Windows configuration-file location for your system.

Expected outcome

The Fetcher MCP server is configured in Claude Desktop, with the documented browser prerequisite installed.

Guide limitations

  • The guide documents installation and configuration, not a tested client connection or a page-fetch run.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
jae-jae/fetcher-mcp · Official homepage title · retained in its source language
How we review sourcesSuggest a correction