switch402 Guides: Pay-per-Call Web Scraping How-Tos
Step-by-step guides with runnable code against the live API: Python, MCP clients and paying HTTP 402 with x402.
- Scrape a website to markdown in Python
Fetch any public page as clean markdown from Python with one HTTP call. You pay $0.008 per successful page in USDC on Base over x402; there is no signup or API key.
- Add web scraping to Claude Desktop (MCP)
Connect Claude Desktop to switch402's remote MCP endpoint so Claude can see its nine tools: scrape, scrape_lite, map, metadata, screenshot, screenshot_full, search, pdf and quote. Read the payment note first: paid tools need an x402-capable client.
- Add web scraping to Cursor (MCP)
Add switch402's remote MCP endpoint to Cursor's mcp.json so the agent can call its nine tools: scrape, scrape_lite, map, metadata, screenshot, screenshot_full, search, pdf and quote. Read the payment note first: paid tools need an x402-capable client.
- Pay per request with x402 and USDC
x402 turns HTTP 402 Payment Required into a machine-readable price. Here is switch402's real 402 response and the code an agent uses to pay it and get the page.
- Web search MCP in Claude Code
Add switch402 to Claude Code with one command and Claude Code gets a search tool (up to 10 ranked results, $0.008 per call) plus scrape_lite to read the pages it finds ($0.003 per call). Read the payment note first: paid tools need an x402-capable client.
- Web scraping in n8n, pay per use
Scrape pages to markdown inside an n8n workflow with the built-in HTTP Request node and a prepaid switch402 key. Each successful page debits $0.003 on /v1/scrape/lite (or $0.008 on /v1/scrape); failed pages cost nothing.
- LangChain web scraper tool
Give a LangChain agent two tools: web_search (up to 10 results, $0.008 per call) and read_url (page to markdown, $0.003 per call). Your code pays each call over x402 in USDC on Base, so there is no API key to manage and failed calls cost nothing.
- CrewAI web scraping tool
Write a small CrewAI custom tool that turns any public URL into markdown for $0.003 per successful call over x402 (USDC on Base). No API key, no plan, and nothing is charged when a page does not come back.
- PDF text extraction in Python
Extract the text of a public PDF from Python without installing a PDF library: POST the URL to /v1/pdf and get the text page by page, up to 50 pages and 10 MB per call. $0.008 USDC on Base per call over x402, charged only when text comes back.