Tools / Web & data
Web Extract $0.005 / call
Clean readable text from any web page.
GET /v1/extractFetches the URL server-side, strips navigation, scripts, and boilerplate with a streaming HTML parser, and returns the title, description, and readable body as markdown-flavored text plus a word count. Built for agents feeding page content into an LLM without the markup noise.
Parameters
url required | Public http(s) URL to fetch |
Example
macOS / Linuxcurl -s "https://quartermaster.surewhynot.app/v1/extract?url=https://example.com"curl.exe -s "https://quartermaster.surewhynot.app/v1/extract?url=https://example.com"Unpaid, these return 402 Payment Required with the payment details in the header (add -i to see them). curl.exe ships with Windows 10+ and works in cmd and both PowerShell versions. To actually pay, use an x402 client (see Connect) or call it as the MCP tool. Cost: $0.005 per call.
FAQ
How is this different from just fetching the URL myself?
Raw HTML is mostly markup an LLM has to wade through. This returns only the readable content, already cleaned and structured, so you spend tokens on the page, not the tags.
How do I pay for this endpoint?
Call it with no payment and you receive HTTP 402 with machine-readable payment requirements. Attach a USDC payment on Base with any x402 client (for example @x402/fetch) and retry — the whole loop is two requests. This call costs $0.005 in USDC.
Do I need an account or API key?
No. There are no accounts, logins, or API keys anywhere in Quartermaster. Payment is per call over the x402 protocol; your wallet is your identity.
Can I call this as an MCP tool instead?
Yes. Quartermaster is also an MCP server at /mcp, so any MCP client (Claude Code, Claude.ai, Cursor) can mount this tool. See /connect for setup.