Skip to main content
MCP server CX Codex

codearia-sieve — Claude Code MCP server: purpose and setup

The codearia-sieve MCP server turns web pages into structured facts and source-linked text chunks. Use it when an agent needs page content without feeding the full HTML to a model.

MIT ★ 5 updated 2026-09-22

Install into Claude Code · Platform CLI All methods and platforms ↓
claude mcp add codearia-sieve -- npx -y codearia-sieve
Open on GitHub

What codearia-sieve does

codearia-sieve strips page furniture such as menus and banners, then extracts dates, numbers paired with units, and ordered content blocks. Each text chunk reports its token and character size and includes an anchor for checking the original page. Optional tracing lists removed elements and the reasons they were discarded.

The pipeline uses ordinary code; it does not start a browser or call a model by default. HTML parsing uses linkedom, while Defuddle handles cleanup and Readability is used if that produces an empty result. Chunks follow two default limits: 20 000 tokens and 50 000 characters. The server checks robots.txt first and reports refusals rather than bypassing them, so pages disallowed there will not be fetched.

What it helps with

  • strip menus and banners from fetched pages
  • extract dates and unit-bearing values
  • split page content into source-linked chunks
  • compare token counts before and after processing

Example prompts for the agent

  • Use codearia-sieve to parse this page and return facts with source anchors.
  • Run this page through codearia-sieve and list its dates, measured values, and warnings.
  • Use codearia-sieve to compare the page size before and after processing, including anchors for key passages.

How to install codearia-sieve

Platform CLI

claude mcp add codearia-sieve -- npx -y codearia-sieve

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about codearia-sieve

How do I install codearia-sieve in Claude Code?

Run claude mcp add codearia-sieve -- npx -y codearia-sieve.

What does codearia-sieve do?

It cleans web pages, extracts dates and values with units, and groups the remaining text into chunks linked to their source locations.

Does codearia-sieve bypass robots.txt restrictions?

No. It checks robots.txt first and reports a refusal instead of bypassing it.

Similar MCP servers

All MCP servers for Agent setup: memory, context, orchestration →

Project sponsors

Companies that keep this analytics open