Extract MCP Server

by averra Your server? Claim it

local only

Extract runs on your own machine — the client starts it, so there is no endpoint to ping. 114 installs a week from npm. Last commit 11 Apr 2026.

URL-to-Markdown API for AI pipelines — clean markdown with metadata and caching.

Installs per day peak 33 · avg 11 · +115% w/w

a month agotoday

114

Installs / week

npm · @averra/extract-mcp

Stars

0 open issues

11 Apr 2026

Last commit

no releases in 90 days

MIT

License

TypeScript

Nothing serious here today

Today is the operative word: we check Extract every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add extract -- npx -y @averra/extract-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "extract": {
      "command": "npx",
      "args": [
        "-y",
        "@averra/extract-mcp"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.extract]
command = "npx"
args = ["-y", "@averra/extract-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "extract": {
      "command": "npx",
      "args": [
        "-y",
        "@averra/extract-mcp"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "extract": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@averra/extract-mcp"
      ]
    }
  }
}

Alternatives to Extract

same job, measured the same way

Scrapiq

by scrapiq

Any URL to clean text, markdown, or JSON for LLM/RAG pipelines.

1 tools answering

Scraper

by ofershap

Web scraping MCP — extract clean markdown, links, and metadata from any URL.

82 installs/wk local only

Web Fetcher

by vojtisprime11

Turns any web page into clean Markdown, page metadata and classified links for LLMs.

34 installs/wk local only

News Article Extractor

by dataleadspro

Extract clean article text, titles, and metadata from news URLs - ready for NLP pipelines.

1 tools answering

Fetchgate

by fetchgate

Fetch any URL as clean Markdown or metadata, and buy digital goods via x402 — for AI agents.

10 tools answering

Scrapi

by bamchi

Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.

35 installs/wk 5 tools answering

Onto

by ravixalgorithm

Clean Markdown and AI-readability scoring for any URL. Built for AI agents.

77 installs/wk answering

JsonLink

by mauriblint

Web access for AI agents: URL to Markdown, link metadata, screenshots, links and images of any URL.

58 installs/wk local only

Extract — questions

Answers built from our own checks of this server.

Why is there no uptime for Extract?

Extract runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @averra/extract-mcp was installed 114 times last week.

How do I connect Extract?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls @averra/extract-mcp straight from npm; nothing to host, nothing to sign up for.

How many people use Extract?

The npm package @averra/extract-mcp was installed 114 times in the last week. Week over week that is +115%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Extract open source?

Yes — it is published under the MIT licence, written in TypeScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.