# Grabber > Grabber is a web page API for AI agents: one GET request turns a public URL into clean Markdown, HTML, plain text, links or metadata. $0.001 a page, $0.005 with JavaScript rendering, prepaid with no subscription, and errors are free. Page links below go to Markdown. Each page of https://grabber.sh/ has a Markdown twin at its path plus `.md` (`/index.md` for the home page), and the page URL itself answers in Markdown to `Accept: text/markdown`. - API: `GET https://api.grabber.sh/fetch` with `Authorization: Bearer gsh_...` - MCP server: https://mcp.grabber.sh (Streamable HTTP, the same key) - API keys: https://dashboard.grabber.sh/keys ($1 of free credit on sign-up, no card) - Setup for agents: https://grabber.sh/skill.md ## Docs - [Grabber API docs](https://grabber.sh/docs.md): Get started with the Grabber API: one GET request turns any URL into Markdown, HTML, text or links. Quickstart, code samples, parameters and errors. - [Authentication](https://grabber.sh/docs/authentication.md): Every Grabber API request needs an API key in the Authorization header. How to create a key, send it, keep it safe and read a 401 response. - [Request parameters](https://grabber.sh/docs/parameters.md): Every parameter of GET /fetch: url, formats, unwrap, includeMetadata and js_render, plus the response envelope and metadata fields you get back. - [Errors](https://grabber.sh/docs/errors.md): Every error the Grabber API returns, with its HTTP status, its stable detail code and what to do next. Errors are never charged. - [Pricing and limits](https://grabber.sh/docs/pricing-and-limits.md): What a Grabber API request costs, when you are charged, how prepaid credit works, and the rate, size and time limits of every request. ## Agents - [Give your agents the web with one MCP server](https://grabber.sh/mcp.md): Add Grabber's remote MCP server to Claude, Cursor, VS Code or Windsurf, and your agent can read any web page as Markdown. $0.001 per page. - [skill.md](https://grabber.sh/skill.md): Setup and use in one file: the key, a request, every parameter, the errors and the costs. - [auth.md](https://grabber.sh/auth.md): How an agent gets and sends a Grabber API key. - [OpenAPI](https://grabber.sh/openapi.json): The API contract for GET /fetch, as OpenAPI 3.0 JSON. - [MCP server card](https://grabber.sh/.well-known/mcp/server-card.json): Endpoint, transport, authentication and tools of the MCP server at https://mcp.grabber.sh. ## Product - [Connect Your Agents To Every Web Page](https://grabber.sh/index.md): One API call turns any URL into clean Markdown for your AI agents. $0.001 per page, no subscription, and failed requests are free. - [Pay for pages, not plans](https://grabber.sh/pricing.md): Grabber costs $0.001 per page and $0.005 with JavaScript rendering. Prepaid credit, no subscription, no minimum, failed requests free. ## Formats - [Turn any URL into clean Markdown](https://grabber.sh/url-to-markdown.md): Convert any web page or PDF into clean Markdown with one API call, ready for LLMs, RAG and AI agents. $0.001 per page, no subscription, errors free. - [Plain text from any web page](https://grabber.sh/html-to-text.md): Extract clean plain text from any web page with one API call: no tags, no scripts, no styles. Built for search, classification and AI. $0.001 per page. - [Extract every link from any page](https://grabber.sh/link-extractor.md): Get every link on a web page as a JSON list of absolute URLs, with one API call. Build crawlers, audits and agents that navigate. $0.001 per page. - [Page metadata in one request](https://grabber.sh/metadata-extractor.md): Extract the title, description, Open Graph tags, JSON-LD, emails and phone numbers of any URL with one API call. $0.001 per page, errors free. - [Render JavaScript before you read the page](https://grabber.sh/javascript-rendering.md): Load React, Vue and other single-page apps in a headless browser and get the rendered page as Markdown, HTML or text. $0.005 per page, errors free. ## Compare - [How Grabber compares](https://grabber.sh/alternatives.md): Grabber compared with Firecrawl, Jina Reader, Tavily Extract, ScrapingBee, Scrape.do, Apify and ZenRows on price, plans, free tiers and MCP. - [Grabber vs Firecrawl](https://grabber.sh/alternatives/firecrawl.md): Grabber vs Firecrawl: price per page, plans, free tiers, failed requests, formats and MCP, side by side. Checked October 2026. - [Grabber vs Jina Reader](https://grabber.sh/alternatives/jina-reader.md): Grabber vs Jina Reader: price per page, plans, free tiers, failed requests, formats and MCP, side by side. Checked October 2026. - [Grabber vs Tavily Extract](https://grabber.sh/alternatives/tavily-extract.md): Grabber vs Tavily Extract: price per page, plans, free tiers, failed requests, formats and MCP, side by side. Checked October 2026. - [Grabber vs ScrapingBee](https://grabber.sh/alternatives/scrapingbee.md): Grabber vs ScrapingBee: price per page, plans, free tiers, failed requests, formats and MCP, side by side. Checked October 2026. - [Grabber vs Scrape.do](https://grabber.sh/alternatives/scrape-do.md): Grabber vs Scrape.do: price per page, plans, free tiers, failed requests, formats and MCP, side by side. Checked October 2026. - [Grabber vs Apify](https://grabber.sh/alternatives/apify.md): Grabber vs Apify Website Content Crawler: price per page, plans, free tiers, failed requests, formats and MCP, side by side. Checked October 2026. - [Grabber vs ZenRows](https://grabber.sh/alternatives/zenrows.md): Grabber vs ZenRows: price per page, plans, free tiers, failed requests, formats and MCP, side by side. Checked October 2026. ## Blog - [The Grabber blog](https://grabber.sh/blog.md): Guides for giving AI agents clean web data: Markdown for RAG, when a page needs JavaScript rendering, MCP setup, and what each one costs. - [Give Claude and Cursor Web Access With an MCP Server](https://grabber.sh/blog/mcp-web-access-for-claude-and-cursor.md): Connect Cursor, Claude Code, Claude Desktop, VS Code or Windsurf to the web with Grabber's remote MCP server. Setup, tools, prompts and cost. - [Static Fetch vs JavaScript Rendering: When You Need a Headless Browser](https://grabber.sh/blog/static-fetch-vs-javascript-rendering.md): Most pages don't need a headless browser. How to tell when one does, what each costs, and a static-first fallback that cuts the bill. - [Turn Any Web Page Into Clean Markdown for RAG](https://grabber.sh/blog/web-page-to-markdown-for-rag.md): Why Markdown beats raw HTML for retrieval, how to fetch any URL as Markdown, and how to chunk it by headings in Python and Node.js. ## Optional - [llms-full.txt](https://grabber.sh/llms-full.txt): Every page above in one Markdown file. - [Blog feed](https://grabber.sh/blog/rss.xml): New posts as an Atom feed.