GoKawiilScry launches programmable web search API with MCP support and congestion pricing
Scry is a new search-over-the-web service built for AI agents, exposed through the Model Context Protocol as well as a direct HTTP API. Developers connect tools like Claude Code, Codex, or Cursor to a single MCP endpoint, authenticate via OAuth or an API key, and query a rolling crawl of high-information web pages using a SQL-like interface. The service also introduces congestion-based pricing tied to usage load.
GoKawiil's interpretation of the reporting above, not reported fact.
As AI agents increasingly need live, structured access to the web rather than static search results, tools like Scry aim to fill the gap between traditional search engines and agent-friendly data retrieval. Congestion pricing signals an attempt to manage compute costs as agentic querying scales, a model that could become common as more autonomous systems hit search infrastructure directly.
- Scry offers programmatic web search accessible via MCP or a direct HTTP API for AI agents.
- It maintains a rolling crawl of allowlisted high-information sites with timestamped freshness for post-cutoff queries.
- The service uses congestion pricing, adjusting costs based on system load rather than flat per-query fees.
Source: scry.io, 2026-09-17
Published there as: “Show HN: Scry, programmable internet search w/ congestion pricing”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.