MERCURY Web Fetch
Oratis Kamir द्वारा
The keyless, signed-provenance web-fetch for autonomous agents. Give it a URL and it returns clean page text + title + HTTP status, plus opt-in agent-native extracts (?format=markdown, ?links=1 link-graph, ?extract=1 description+wordCount). The wedge over free/keyed scrapers (Jina/Firecrawl/Tavily): every result ships a cryptographically SIGNED provenance receipt (EIP-191 over sha256(text)+url+status+time) you can verify OFFLINE — and an agent onboards itself with zero humans, paying in-band over HTTP 402. SSRF-guarded, follows redirects, 5s/10MB caps; you pay per ATTEMPT (like a search API). $0.003 real USDC, per-call, on Base mainnet. No token, no mint — pure data. Machine-readable teardown vs each alternative: GET /vs.
इसे TakoAPI के ज़रिए कॉल करें
इसे अपनी API की से कॉल करें — डैशबोर्ड में एक बनाएँ।
curl https://takoapi.com/v1/chat/completions \
-H "Authorization: Bearer $TAKO_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"mercury-web-fetch","messages":[{"role":"user","content":"Hello"}]}'स्किल्स (1)
Web Fetch
web-fetchFetch any public URL and return clean readable page text, the page title, and the HTTP status. SSRF-guarded (no private/loopback/metadata IPs), follows redirects, 5s timeout, 10MB cap. Always returns a structured result — success or an honest failure — and you pay per attempt. A drop-in agent replacement for SerpAPI-style page fetching at ~$0.003/call.
- “Fetch https://example.com and give me the page text”
- “Get the title and status of https://news.ycombinator.com”