Skip to content
Agentmart
Submit a tool

Best MCP servers for data extraction

We found 81 MCP servers for data extraction in the catalog; these are the 15 that rank highest. The order comes from our rank, which weighs adoption, freshness, documentation and publisher identity. Nobody can pay for a place on this list. Browser Use, Skyvern and Apify MCP Server lead it. Browser Use, Apify MCP Server and ScrapingBee are published by the company that makes them. Browser Use has the most GitHub stars here (119,023). 13 of the 15 had activity in the last 30 days. Remote servers need no local install; local ones run on your machine and can reach local files. Each entry lists why it made the list and links to its install page.

Updated Oct 26, 2026 · Built from catalog data; how we rank and grade

Top 15 of 81

  1. 1
    Browser Use

    browser-use.comOfficial

    Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.

    • Published by the vendor
    • Most GitHub stars here (119,023)
    • Most weekly downloads here (1.5M)

    ★ 119K↓ 1.5M/wkLast active Oct 22, 2026Local (stdio), Remote (HTTP)Claude Code, VS Code, Codex, Cursor +2

  2. 2
    Skyvern

    Skyvern-AI

    AI-powered browser automation — navigate, click, fill forms, and extract data from any website.

    • 23.3K GitHub stars
    • Remote server, no local install
    • Active in the last 30 days

    ★ 23.3KLast active Oct 24, 2026Remote (HTTP)Claude Code, VS Code, Cursor, Windsurf

  3. 3
    Apify MCP Server

    apify.comOfficial

    Extract data from any website with thousands of scrapers, crawlers, and automations on Apify Store

    • Published by the vendor
    • 12.9K GitHub stars
    • Remote server, no local install

    ★ 12.9KLast active Oct 24, 2026Remote (HTTP)Claude Code, VS Code, Cursor, Windsurf

  4. 4
    Fitter

    PxyUp

    Turn any website or API into structured JSON with LLM-authored declarative scraping configs.

    • Open source (MIT)

    ★ 133Last active Aug 26, 2026Local (stdio)Claude Code, Codex, VS Code, Claude Desktop +2

  5. 5
    ScrapingBee

    scrapingbee.comOfficial

    Scrape any web page, search Google/Amazon/Walmart/YouTube and extract data via the ScrapingBee API.

    • Published by the vendor
    • Remote server, no local install
    • Active in the last 30 days

    Last active Oct 9, 2026Remote (HTTP)Claude Code, VS Code, Cursor, Windsurf

  6. 6
    Scrapegraph MCP

    ScrapeGraphAI

    AI-powered web scraping and data extraction capabilities through ScrapeGraph API

    • Open source (MIT)

    ★ 117↓ 141/wkLast active Jul 17, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  7. 7
    Scrapfly

    mcp.scrapfly.io

    Scrape any website, extract structured data, and collect web content at scale with AI agents

    • Active in the last 30 days

    ★ 14Last active Oct 23, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  8. 8
    Talonic

    talonicdev

    Extract structured, schema-validated data from PDFs, scans, images, spreadsheets, and forms.

    • Active in the last 30 days
    • Open source (MIT)

    ★ 5Last active Oct 21, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  9. 9
    Fantoma

    Huzy85

    Accessibility-tree browser for AI agents: read pages, log in, extract data, run tasks.

    • Active in the last 30 days
    • Open source (MIT)

    ★ 7↓ 99/wkLast active Oct 13, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  10. 10
    Extend

    extend.aiOfficial

    Turn documents into structured data: parse, extract, classify, split, and fill PDF forms.

    • Published by the vendor
    • Remote server, no local install
    • Active in the last 30 days

    ★ 2Last active Oct 20, 2026Remote (HTTP)Claude Code, VS Code, Cursor, Windsurf

  11. 11
    SchemaSure — structured extraction

    noamjose

    Extract schema-valid JSON from text/HTML or document images.

    • Active in the last 30 days
    • Open source (MIT)

    ↓ 66/wkLast active Oct 15, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  12. 12
    Sezzlee PDF

    sezzlee

    Extract text from local PDF documents with optional pluggable OCR.

    • Active in the last 30 days
    • Open source (MIT)

    ★ 1Last active Oct 13, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  13. 13
    HWP to Markdown

    groove79

    Convert Korean HWP/HWPX (한글) documents to Markdown and extract tables.

    • Active in the last 30 days
    • Open source (MIT)

    ↓ 41/wkLast active Oct 23, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

  14. 14
    Mervext

    vstudiodigital.com

    Extract invoices, receipts and contracts into structured JSON.

    • Remote server, no local install
    • Active in the last 30 days
    • Open source (MIT)

    Last active Oct 9, 2026Remote (HTTP)Claude Code, VS Code, Cursor, Windsurf

  15. 15
    KitchenSink4Web

    KitchenSink4AI

    Browser MCP server: budgeted page reads, honest unread accounting, structured extraction.

    • Active in the last 30 days
    • Open source (AGPL-3.0)

    ↓ 36/wkLast active Oct 13, 2026Local (stdio)Claude Code, Codex, VS Code, Cursor +2

Related