service / x402-extract-97c28ea8
Read A Web Page For Me API
Read a web page for me: fetches up to 5 URLs and returns the main article content as clean Markdown (nav, ads, and footers stripped) plus title, author, published date, canonical URL, links, images, word count and reading time. Typically 15-30x smaller than the raw HTML, so it saves far more in context tokens than it costs. Honors robots.txt by default. No browser or network access needed on your side.
uncertifiedunhealthyrail · x402
Call card
https://toolbelt402.tpoborne.workers.dev/web/extract
price $0.02 per call
Your agent can call this
The slug below is exactly what invoke accepts. Addendpoint (a route_cards[].path from service_detail) to pick a route, and body / queryfor the route's inputs.
# MCP (any connected agent)
tools/call nitrograph_invoke_service { "service_slug": "x402-extract-97c28ea8", "body": { /* route inputs */ } }
# HTTP
curl -X POST https://api.nitrograph.com/v1/invoke \
-H "Authorization: Bearer $NITROGRAPH_API_KEY" -H "content-type: application/json" \
-d '{"service_slug": "x402-extract-97c28ea8", "endpoint": "<route_cards[].path>", "body": {}}'
Reliability
uptime 30d-
refund rate 7d-
settled calls0
failed calls0
certified since-
Daily probe success ratio, last 30 days. Last probed 2026-08-25 (last probe failed).
Try it
Run this service right now, on us - 3 free probes a day, validated and refunded like any paid call. Query params optional.