Fetch
Retrieve web pages and convert them to clean markdown.
What it does
Fetches a URL and returns the page content converted to markdown, stripping ads, navigation, and irrelevant markup.
Why it matters
Reading web pages is a fundamental research task. This MCP makes any URL readable in a model context without browser overhead.
Best for
- Documentation reading
- Article summarization
- Public web page extraction
- Link analysis
- Text extraction
Not ideal for
- JavaScript-heavy SPAs
- Login-required pages
- Real-time web search
When to use it
When you need to read documentation, articles, or any public web page inside an AI conversation.
When not to use it
When pages are behind authentication, require JavaScript rendering, or return dynamic content that needs a real browser.
Key features
- No API key required
- HTML to markdown conversion
- Fast setup
- Clean text extraction
- Official Anthropic support
Frequently asked questions
Does it require any API key?
No. The Fetch MCP makes standard HTTP requests with no authentication required.
Can it handle JavaScript-rendered pages?
No. It makes a plain HTTP fetch. For JS-rendered pages, use the Puppeteer MCP instead.
Install
$ npx -y @modelcontextprotocol/server-fetchScores
Details
- Pricing
- open source
- Setup time
- 1 min
- Complexity
- Low
Works with
Alternatives
- Brave Search →
Real-time web search with privacy-focused results.
- Puppeteer →
Full browser automation: navigate, click, screenshot, and scrape.
More Web Research MCPs
Other tools in the same category worth evaluating.
Exploring Top MCPs for Web Research? See all Web Research MCPs →