Parses a web page into the exact format a decision model needs: dates as dates, numbers with units, chunks that fit the model's window. MCP server + TypeScript library, no model or API key required.
Parses a web page into the exact format a decision model needs. Dates as dates. Numbers with units. Text in chunks that fit the model's window, each pointing back to where it came from. One call — and the token bill, before and after.
Measured, not promised. A live run over random pages picked the same day — fresh news from RSS feeds in several languages, random Wikipedia articles, docs, blogs, government sites, recipes, shops. Every row is in bench/analytics/, and npm run analytics reruns the whole thing. The output was then put in front of a decision model: see Checked by a judge.
An agent that needs a web page fetches the whole thing: navigation, cookie banner, footer, ad slots, a megabyte of framework markup. Then a model paid per token digs through the pile for one paragraph.
codearia-sieve does the digging before the model sees anything — and returns the page as state, not prose:
"Published September 15, 2026" → "2026-09-15". Read from JSON-LD, meta tags and first; from a byline only when the markup is silent, and never guessed.
"$42 per billion tokens" → { value: 42, unit: "USDperbillion" }. Works in nine languages; the decimal comma follows the page's language. A number without a unit is not a fact. A year is never a fact.
Each chunk knows its size in tokens and characters, the blocks it was built from, and the anchor on the page where a decision can be checked.
Everything else — menus, footers, banners, tag rows, "read more" — is removed, and with trace: true you get the list of what was removed and why.
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/AntonG87--codearia-sieve.html)
MCP server that turns web pages into clean Markdown, keeping tables, code blocks, and images intact. Agents can fetch pages, save docs to your project or a global library, and crawl whole doc sites.
tiliondev/waystoneBrowser action recorder for automation: record a task once, replay it, or hand the folder to an agent
herry2059/project-os-for-codexOpen-source control plane for Codex projects: Git-backed context, visible agent progress, scoped MCP access, resumable work, and safe handoffs.
Cripacx/mediagenAI image and video generation skill for Claude Code and other coding agents — Gemini, OpenAI and Kie AI behind one CLI and MCP server, with EU AI Act content marking.
howznguyen/pi-delegate-mcpMCP server that turns the pi coding agent into a steerable background worker: delegate a task, redirect it mid-run, and keep its context out of your own.
klarluft/gitwarren-appA cross-platform desktop app for doing local code reviews of your own git repositories. Single user, single machine, no server, no account.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.