Fetch MCP Server

Retrieves web content in various formats via HTTP.

Local serverstdioTypeScript 3

What is the Fetch MCP server?

Fetch MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Retrieves web content in various formats via HTTP.

What you get

This MCP server provides functionality to fetch web content in various formats, including HTML, JSON, plain text, and Markdown.

  • Fetches web content using modern fetch API
  • Supports custom headers for requests
  • Provides content in multiple formats: HTML, JSON, plain text, and Markdown
  • Uses JSDOM for HTML parsing and text extraction
  • Uses TurndownService for HTML to Markdown conversion

What the assistant can call

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

  • fetch_html — Fetch a website and return the content as HTML
  • Input — - url (string, required): URL of the website to fetch
  • fetch_json — Fetch a JSON file from a URL
  • fetch_txt — Fetch a website and return the content as plain text (no HTML)
  • fetch_markdown — Fetch a website and return the content as Markdown
  • Tools — The Tools tool exposed by this server
  • Resources — This server does not provide any persistent resources. It's designed to fetch and transform web content on demand
  • Usage — The Usage tool exposed by this server

Setting it up

@smithery/cli on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Choosing this one

Among the search and retrieval options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Fetch's toolset — fetch_html, Input, fetch_json and 5 more — is a fair guide to whether it matches your workflow. It is maintained by goswamig; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

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.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the fetch mcp server does with a few real requests.

Available tools

ToolWhat it does
fetch_htmlFetch a website and return the content as HTML
Input- url (string, required): URL of the website to fetch
fetch_jsonFetch a JSON file from a URL
fetch_txtFetch a website and return the content as plain text (no HTML)
fetch_markdownFetch a website and return the content as Markdown
ToolsThe Tools tool exposed by this server.
ResourcesThis server does not provide any persistent resources. It's designed to fetch and transform web content on demand.
UsageThe Usage tool exposed by this server.

How to install the Fetch MCP server

{
  "mcpServers": {
    "fetch-2": {
      "command": "npx",
      "args": ["-y", "@smithery/cli"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Fetch to fetch html.
  • Use Fetch to Input.
  • Use Fetch to fetch json.

Frequently asked questions

Fetch can retrieve web content in HTML, JSON, plain text, and Markdown formats, providing versatility for different data needs.