FRENES

Web search and extraction · MCP server

Codearia sieve: MCP server, setup and security

Codearia sieve is an open-source MCP server published on GitHub that lets an AI agent extract structured facts from web pages within a defined token budget. Its repository has 5 stars and its last commit is from September 22, 2026 and it is licensed under MIT.

Actively maintained

What Codearia sieve does

According to its repository: “Deterministically convert web pages into decision-ready state: ISO dates, numbers with units as facts and token-budgeted chunks anchored to the page.”

The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. Codearia sieve is listed under Web search and extraction, a category of 159 servers in the directory, where it ranks #132 by stars.

Topics declared by the repository: ai-agents, claude-code, content-extraction, context-engineering, html-to-markdown, llm-agents.

Installing and connecting Codearia sieve

Distribution modes declared in the official MCP registry:

  • npm package (Node.js, usually started with npx)

It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: TypeScript.

Security: what to check

Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.

None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to Codearia sieve. That does not replace reading the code.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on September 20, 2026, the AntonG87/codearia-sieve repository has 5 stars and 1 forks, with 5 open issues. It has more stars than 13% of the servers in the directory. Last change 1 month ago. Version published in the registry: 0.2.2 (September 22, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

WigoloWigolo : 5.5K5.5KExa MCP serverExa MCP server : 5.2K5.2KJobSpyJobSpy : 4.6K4.6KTolgeeTolgee : 4.1K4.1KArxiv MCP serverArxiv MCP server : 3.2K3.2KTrieveTrieve : 2.7K2.7KTavily MCPTavily MCP : 2.5K2.5KOpen webSearchOpen webSearch : 1.9K1.9KCodearia sieveCodearia sieve : 55
GitHub stars of the most followed servers in the category (log scale); Codearia sieve in orange. Checked October 25, 2026.

Verdict

Codearia sieve is a reasonable choice; check the points below before connecting it.

Strengths

  • Active project: recent commit
  • Listed in the official MCP registry
  • Permissive licence (MIT)

Limitations

  • Few visible users

Frequently asked questions

How do I install Codearia sieve?

Codearia sieve is distributed as npm package (Node.js, usually started with npx). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of AntonG87/codearia-sieve.

Is Codearia sieve free?

The code is published under the MIT licence and can be used free of charge.

Is Codearia sieve safe?

No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.

Is it an official server?

Nothing says so: it is a project published by AntonG87 on GitHub. Check who maintains it before giving it access.

What are the alternatives to Codearia sieve?

In the same category: Exa MCP server, Brave search MCP server, Arxiv MCP server, and JobSpy. Exa MCP server and Brave search MCP server score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score