Web MCP Server

MCP server for web content fetching, summarizing, comparing, and extracting information

Local serverstdio

What is the Web MCP server?

Web MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. MCP server for web content fetching, summarizing, comparing, and extracting information.

What you get

A Model Context Protocol (MCP) server that provides web content fetching, summarization, comparison, and extraction capabilities.

  • Three Core Tools — Provides summarize_web, compare_web, and extract_web for versatile web content processing
  • Handles Multiple URLs — Process up to 20 URLs in a single request
  • Content Transformation — Converts HTML to clean, readable text and automatically resolves GitHub /blob/ URLs to their raw content equivalent
  • Safe & Secure — Protects against Server-Side Request Forgery (SSRF) by blocking requests to private IP addresses
  • Configurable — Allows setting timeouts and content length limits to manage performance

Setting it up

The server ships on npm as web-fetch-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

What the assistant can call

Once Web is connected, these are the calls the assistant has available:

  • Configurable — Allows setting timeouts and content length limits to manage performance
  • summarize_web — Summarizes content from one or more URLs
  • compare_web — Compares content across multiple URLs
  • extract_web — Extracts specific information from web content using natural language prompts

Configuration and credentials

You will need 2 environment variables: GEMINI_API_KEY, YOUR_GEMINI_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the web mcp server does with a few real requests.

Choosing this one

Plenty of search and retrieval servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Web's toolset — Configurable, summarize_web, compare_web and 1 more — is a fair guide to whether it matches your workflow. It is maintained by KylinMountain; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
ConfigurableAllows setting timeouts and content length limits to manage performance.
summarize_webSummarizes content from one or more URLs.
compare_webCompares content across multiple URLs.
extract_webExtracts specific information from web content using natural language prompts.

How to install the Web MCP server

{
  "mcpServers": {
    "web-fetch-server": {
      "command": "npx",
      "args": ["-y", "web-fetch-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-value",
        "YOUR_GEMINI_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
GEMINI_API_KEYCredential the server authenticates with.Yes
YOUR_GEMINI_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Web to Configurable.
  • Use Web to summarize web.
  • Use Web to compare web.

Frequently asked questions

It connects Web to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (Configurable, summarize_web, compare_web, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Web directly.