data extraction mcp servers

38 tagged data extraction, measured the same way as everything else here.

Browse within: instagram 8claude-plugin 7douyin 7

brightdata-mcp

01

brightdata/brightdata-mcp

MCP server Claude CodeCodexCursor +2

Bright Data's Web MCP server enabling AI agents to search, extract & navigate the web. Runs locally from the @brightdata/mcp npm package. Needs 9 environment variables to run.

2.6k +2 20d ago A tokens not measured original MIT

crw

02

us/crw

MCP server Claude CodeCodexCursor +2

MCP server for CRW web scraper — scrape, crawl, map, extract, search, and PDF-parse tools for AI agents. Runs locally from the crw-mcp npm package.

882 2d ago A tokens not measured AGPL-3.0

fastcrw

03

us/crw

MCP server Claude CodeCodexCursor +2

Scrape, crawl, map & search the web. Open-source, self-hostable Rust crawler & search for AI agents. Remote server at fastcrw.com.

882 2d ago A tokens not measured AGPL-3.0

xquik

04

Xquik-dev/x-twitter-scraper

MCP server Claude CodeCodexCursor +2

MCP server "xquik", hosted remotely at xquik.com, as configured in Xquik-dev/x-twitter-scraper.

191 5d ago A tokens not measured original MIT

zenrows-mcp

05

ZenRows/zenrows-mcp

MCP server Claude CodeCodexCursor +2

Zenrows MCP server — Fetch, Extract, Batch, and Browser Sessions for AI coding assistants. Runs locally from the @zenrows/mcp npm package. Needs 1 environment variable to run.

19 11d ago A tokens not measured original MIT

xcatcher

06

lvpiggyqq/xcatcher-mcp-manifest

MCP server Claude CodeCodexCursor +2

Fetch recent public X/Twitter posts by named handle for monitoring, comparison, OSINT, and research. Remote server at xcatcher.top.

9 22d ago A tokens not measured original MIT

magpipe

07

elagerway/magpipe

MCP server Claude CodeCodexCursor +2

Manage AI voice agents, calls, SMS, contacts, and phone numbers via Magpipe. Runs locally from the magpipe-mcp-server npm package. Needs 1 environment variable to run.

6 5d ago A tokens not measured

tikhub-tiktok

08

TikHub/tikhub-plugin

MCP server Claude CodeCodexCursor +2

MCP server "tikhub-tiktok", hosted remotely at mcp.tikhub.io, as configured in TikHub/tikhub-plugin.

6 2mo ago A tokens not measured original MIT

tikhub-douyin

09

TikHub/tikhub-plugin

MCP server Claude CodeCodexCursor +2

MCP server "tikhub-douyin", hosted remotely at mcp.tikhub.io, as configured in TikHub/tikhub-plugin.

6 2mo ago A tokens not measured original MIT

tikhub-xiaohongshu

10

TikHub/tikhub-plugin

MCP server Claude CodeCodexCursor +2

MCP server "tikhub-xiaohongshu", hosted remotely at mcp.tikhub.io, as configured in TikHub/tikhub-plugin.

6 2mo ago A tokens not measured original MIT

marketplace-search

11

lulzasaur9192/marketplace-search-mcp

MCP server Claude CodeCodexCursor +2

MCP server with 22 tools for marketplace search, price comparison, license verification, childcare costs, estate sales, storage pricing, GSA auctions, home services, FCC lookup, and AI skill safety — TCGPlayer, Reverb, Grailed, Redfin, Poshmark, Craigslis. Runs locally from the @lulzasaur9192/marketplace-search-mcp…

4 5mo ago A tokens not measured

linkedin-mcp-server

12

selvin-paul-raj/Linkedin-MCP-Server

MCP server Claude CodeCodexCursor +2

Model Context Protocol (MCP) server for LinkedIn - enabling AI agents to interact with LinkedIn's professional network. Runs locally from the linkedin-mcp-server Python package.

3 2mo ago A tokens not measured original MIT

company-enrichment

13

Br0ski777/company-enrichment-x402

MCP server Claude CodeCodexCursor +2

Company firmographics from domain: name, socials, tech stack, emails, phone, address. Remote server at company-enrichment.api.klymax402.com.

2 26d ago A tokens not measured original MIT

mysleekdesigns/crawlforge-mcp

MCP server Claude CodeCodexCursor +2

Web scraping, crawling, deep research & autonomous extraction — 29 MCP tools, clean Markdown/JSON. Runs locally from the crawlforge-mcp-server npm package. Needs 3 environment variables to run.

2 yesterday A tokens not measured original MIT

octoparse-mcp

15

octoparse/octoparse-mcp

MCP server Claude CodeCodexCursor

Official Octoparse MCP server for template discovery, cloud tasks, and structured data export. Remote server at mcp.octoparse.com.

1 1mo ago A tokens not measured original MIT

pdf-mcp

16

wesseltl/pdf-mcp

MCP server Claude CodeCodexCursor

An MCP server that lets AI agents extract text and tables from PDFs (invoices, reports, statements). Runs locally from the pdf-agent-mcp Python package.

1 19d ago A tokens not measured original MIT

crawlora

17

Crawlora-org/crawlora-mcp

MCP server Claude CodeCodexCursor

MCP server "crawlora", hosted remotely at mcp.crawlora.net, as configured in Crawlora-org/crawlora-mcp.

1 7d ago A tokens not measured original MIT

crawlora-mcp

18

Crawlora-org/crawlora-mcp

MCP server Claude CodeCodexCursor

Hosted MCP: 795 structured web-data tools for search, maps, commerce, social, gaming & finance. Remote server at mcp.crawlora.net.

1 7d ago A tokens not measured original MIT

mcp

19

Synoppy/synoppy-mcp

MCP server Claude CodeCodexCursor

MCP server for the Synoppy web-data API — read, screenshot, crawl, map, search, extract, classify, enrich, and images as tools for any MCP client. Runs locally from the @synoppy/mcp npm package.

1 2mo ago A tokens not measured original MIT

jirosearch

20

DevAnimecx/jiro

MCP server Claude CodeCodexCursor

Local-first, AI-native web search & scraping API. A drop-in, self-hosted SerpAPI alternative with MCP server, agentic research, and built-in legal compliance. Runs locally from the jirosearch Python package.

1 6d ago A tokens not measured original MIT

person-enrichment

21

Br0ski777/person-enrichment-x402

MCP server Claude CodeCodexCursor

Person lookup from email: name, title, company, social profiles. x402. Remote server at person-enrichment.api.klymax402.com.

0 1mo ago A tokens not measured original MIT

tech-enrichment

22

Br0ski777/tech-enrichment-x402

MCP server Claude CodeCodexCursor

Detect 50+ technologies on any website: CMS, frameworks, analytics, CDN. x402. Remote server at tech-enrichment.api.klymax402.com.

0 26d ago A tokens not measured original MIT

web-scraper

23

Br0ski777/web-scraper-x402

MCP server Claude CodeCodexCursor

Extract clean markdown from any URL. Removes boilerplate. For RAG pipelines. x402. Remote server at web-scraper.api.klymax402.com.

0 26d ago A tokens not measured original MIT

proofetch

24

Vektoris-AI/proofetch-mcp

MCP server Claude CodeCodexCursor

Verified extraction: source-backed JSON from PDFs/URLs; honest null + signed receipt. Remote server at proofetch-vektoris-ai-workflows.vercel.app.

0 2mo ago A tokens not measured original MIT