best of · updated August 2026

The 15 best web scraping MCP servers

The 15 web scraping MCP servers worth your time, out of 334 we track - actively maintained, with real adoption, ranked on monthly installs, GitHub stars, and commit recency. Checked nightly.

Web-scraping MCP servers turn URLs into structured data an agent can reason over. Differentiate on JavaScript rendering, anti-bot handling, output formats, and whether the scraper runs locally or via a hosted API.

01 Firecrawl MCP Server ★ 7,310 · commit 2026-08-25 A Model Context Protocol (MCP) server that brings Firecrawl to MCP-compatible AI agents - search, scrape, and interact with the live web for clean, agent-ready context. 512,194 installs/mo · 12 tools documented · needs 2 env vars $ npx -y firecrawl-mcp 02 Tavily MCP ★ 2,351 · commit 2026-08-20 MCP server for advanced web search using Tavily 127,185 installs/mo · needs 3 env vars $ npx -y tavily-mcp 03 Wigolo ★ 4,647 · commit 2026-08-24 Local-first web intelligence for AI agents - no keys, no cloud, no metered bill. 6,345 installs/mo · 10+ releases/90d · needs 7 env vars $ npx -y wigolo 04 Spotifyscraper ★ 298 · commit 2026-08-09 Extract public Spotify data - tracks, albums, artists, playlists, and podcasts - without the official API or an API key. 10,162 installs/mo · 10+ releases/90d · no env vars documented $ uvx spotifyscraper 05 Py Scrappy ★ 191 · commit 2026-08-24 Adaptive Python web scraping toolkit (self-healing, stealth) + MCP server for AI agents. 5,674 installs/mo · 10+ releases/90d · needs 1 env var $ uvx pyscrappy 06 Search1 API ★ 173 · commit 2026-08-19 The official MCP server for Search1API - web search, news, page retrieval, sitemap discovery, and trending topics in one API. 2,877 installs/mo · 7 releases/90d · needs 1 env var $ npx -y search1api-mcp 07 Omnisearch ★ 345 · commit 2026-08-21 A Model Context Protocol (MCP) server that provides unified access to Tavily, Brave, Kagi, Exa AI, GitHub, Linkup, and Firecrawl through four consolidated tools. 1,523 installs/mo · 4 tools documented · 1 release/90d · needs 7 env vars $ npx -y mcp-omnisearch 08 Charlotte ★ 175 · commit 2026-08-21 Your AI agent burns ~50,000 characters of accessibility tree just to look at the Hacker News front page. 1,568 installs/mo · 1 release/90d · needs 1 env var $ npx -y @ticktockbent/charlotte 09 Exa ★ 4,917 · commit 2026-08-21 Connect AI agents to Exa for web search, content fetching, and multi-step research. 4 tools documented · no env vars documented $ claude mcp add exa-labs-exa-mcp-server --transport http https://mcp.exa.ai/mcp 10 Apify MCP Server ★ 4,718 · commit 2026-08-23 Extract data from any website with thousands of scrapers, crawlers, and automations on Apify Store ⚡ 2 tools documented · 10+ releases/90d · needs 4 env vars $ claude mcp add apify-apify-mcp-server --transport http https://mcp.apify.com/ 11 Wet MCP ★ 16 · commit 2026-08-24 Web search, content extraction, and library docs for AI agents -- 5-strategy scraping, runs without API keys. 3,245 installs/mo · 6 tools documented · 4 releases/90d · needs 7 env vars $ uvx wet-mcp 12 Agent402.Tools: pay-per-call web tools ★ 8 · commit 2026-08-25 Framework adapters (drop-in tools for the major agent stacks - auto-payment underneath). 3,075 installs/mo · 6 releases/90d · needs 1 env var $ npx -y agent402-mcp 13 Jobseek ★ 180 · commit 2026-08-25 Open-source job search built from 5,300+ company career sites and ATS feeds. 375 installs/mo · no env vars documented $ npx -y @jseek/mcp-server 14 Zenrows MCP ★ 19 · commit 2026-08-21 The Zenrows MCP (Model Context Protocol) server is the standard way AI systems use Zenrows' web data infrastructure. 1,521 installs/mo · 3 tools documented · needs 1 env var $ npx -y @zenrows/mcp 15 Seo Audit Console ★ 12 · commit 2026-08-19 A technical SEO audit you can hold a conversation with - built from your own Search Console data and a live crawl of your site, run inside Claude. 1,860 installs/mo · 5 releases/90d · no env vars documented $ npx -y @houtini/seo-audit-console

How to choose between them

Firecrawl MCP Server tops the list - the most installs (512,194 last month) and actively maintained. 5 of these 15 offer a remote endpoint (no local process to run); the rest are local stdio servers. 4 document no required env vars - paste the config and go; the others need env vars set first (each page lists exactly which). Where we've compared two of these head-to-head, the comparison is linked on each one's page.

Quick answers

Which web scraping MCP server is most installed?

Firecrawl MCP Server, with 512,194 installs in the last month (as of August 2026).

How many web scraping MCP servers exist?

We track 334 web scraping MCP servers in the official registry. The 15 above are the actively-maintained ones with real adoption - ranked by monthly installs, GitHub stars, and commit recency.

All 78 web scraping MCP servers

Ranked 16 onward, same order as above. Status checked last night.

How this list is ranked

Ranked from live registry + GitHub data: monthly installs (npm/PyPI), GitHub stars, and commit recency - recomputed nightly. No pay-to-rank, ever. The 15 above lead the full list of 78, all of which you can see on this page. The other 256 we track have stopped being maintained, or nobody is using them yet. Full recipe: how we verify.