url-context-mcp

It's designed for AI agents that need to:

- Read a web page as clean markdown (no boilerplate, no nav/footer noise)
- Discover links on a page (with filters) before deciding what to fetch next
- Search pages for specific text/code without reading the whole thing
- Do all of the above in a single call

All tools accept either aurl(server fetches it) or rawhtml(you provide the markup), so they're composable with other fetchers too.

Installation (copy-paste into your MCP client config)

{ "mcpServers": { "url-context": { "command": "npx", "args": ["-y", "url-context-mcp"] } } }

That's it.npx -ydownloads and runs the server on first use; no separate install step needed. Requires Node.js 18+.

Why it's the best design for an AI agent

- Readability-first: defaults to Mozilla Readability extraction so the agent gets the article, not the chrome. Reduces tokens and irrelevance.
- One-call combo:fetch_and_searchreturns content + links + matches together — fewer round trips when an agent wants to "understand this page and find X on it".
- Link discovery before prefetch:extract_linkslets an agent survey a page's destinations and pick the right one to fetch, instead of guessing or fetching everything.
- Regex search with context: agents can locate an error string, an API endpoint, a version number, etc. on a page with bounded context windows.
- No browser, no head: pure HTTP + jsdom. Fast, sandboxed, works anywhere Node runs. No Playwright/Chromium dependency bloat.
- Sane defaults + truncation:maxChars,limit,maxMatcheskeep responses bounded so context windows don't blow up.

npm install node index.js # run the stdio server npm pack # build the publishable tarball

- fetch_image: optional compression.Oversized images can now be shrunk to fit withinmaxSizeKBinstead of being rejected. Setcompress=true(default false) and the image is resized tocompressMaxWidth×compressMaxHeight(defaults 1024×768, aspect preserved) and re-encoded as JPEG (or PNG when the source has an alpha channel or is animated), loweringcompressQuality(1–100, default 75) in steps of 10 until under the limit. Supports tuning viacompressQuality,compressMaxWidth,compressMaxHeight.
- fetch_image: hardened DoS guards.The response body is streamed with a hard byte cap (applied regardless ofcompress), so chunked/ lying-header/infinite bodies can't OOM the server. Image decoding runs withfailOn: "error", an explicitlimitInputPixels(≈26 MP) and rejects via a pre-decode dimension check, blocking decompression bombs. The compression encode loop is bounded by iteration count (6) and a 15 s deadline.
- Server version bumps to 1.3; user-agent string updated accordingly.

- New tool:fetch_image.Resolves an image URL (absolute, or relative to abaseUrl) and returns it as an MCPimagecontent block (base64 with amimeTypederived from the response Content-Type header, falling back to the URL extension). Lets the model actuallyseeimages found in pages marked up in markdown. OptionalmaxSizeKB(default 512 KB) protects the context window from oversized payloads. MIME fallback map covers png/jpg/jpeg/gif/webp/svg/bmp/avif/ico.
- Server version bumps to 1.2; user-agent string updated accordingly.

- Preserve dropped headings in extracted content.Mozilla Readability strips the page<h1>/title from itscontenton minimal pages (e.g.example.com: the# Example Domainheading was never returned byfetch_url, andsearch_contenttherefore couldn't find "Example Domain"). We now detect headings present in the raw body but missing from Readability's cleaned HTML and re-prepend them, so the page title is always part of the returned markdown/text and is searchable.
- search_contentraw-HTML fallback.When a search of the converted (markdown/text) content finds zero matches and raw HTML is available, the tool re-runs the search against the stripped raw text as a safety net. The result flag notes when the fallback path was used ((raw-HTML fallback)in the header).
- Misc: user-agent string bumped to1.1.

Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.

Fetch web content using the Node.js undici library.

An MCP server for web search and content extraction using DuckDuckGo.

One API for Search, Crawling, and Sitemaps

Search for Airbnb listings and get detailed information about accommodations.

Search for products and compare prices at Coles and Woolworths supermarkets in Australia.

Query computer component prices from Taiwan's CoolPC website to generate AI-assisted price quotes.

A product search server that provides markdown-formatted responses with clickable product links and prices.

AI-powered lead generation from Google Maps. Search businesses, enrich with emails/phones/socials, score leads 0-100, export CSV. Free alternative to Apollo.io. No API keys required.

Local business search and lead generation via Google Maps

An MCP server for searching Google Scholar, built for AI assistants and automation workflows that need papers, authors, citations, and BibTeX entries.