best of · updated September 2026

The 15 best web scraping MCP servers

The 15 web scraping MCP servers worth your time, out of 494 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 ★ 7,536 · commit 2026-09-30 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. 297,906 installs/mo · 4 tools documented · needs 2 env vars $ npx -y firecrawl-mcp 02 Tavily MCP ★ 2,416 · commit 2026-09-29 MCP server for advanced web search using Tavily 85,326 installs/mo · needs 3 env vars $ npx -y tavily-mcp 03 Spotifyscraper ★ 324 · commit 2026-09-18 Extract public Spotify data - tracks, albums, artists, playlists, and podcasts - without the official API or an API key. 4,801 installs/mo · no env vars documented $ uvx spotifyscraper 04 Py Scrappy ★ 260 · commit 2026-09-25 Adaptive Python web scraping toolkit (self-healing, stealth) + MCP server for AI agents. 1,771 installs/mo · 10+ releases/90d · needs 1 env var $ uvx pyscrappy 05 Apify MCP Server ★ 8,922 · commit 2026-09-29 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/ 06 Omnisearch ★ 351 · commit 2026-09-30 A Model Context Protocol (MCP) server that provides unified access to Tavily, Brave, Kagi, Exa AI, GitHub, Linkup, and Firecrawl through four consolidated tools. 1,032 installs/mo · 4 tools documented · 2 releases/90d · needs 1 env var $ npx -y mcp-omnisearch 07 Wet MCP ★ 18 · commit 2026-09-30 Open-source MCP server for AI agents: web search, content extraction, and library docs. 5,156 installs/mo · 6 tools documented · 10+ releases/90d · needs 6 env vars $ uvx wet-mcp 08 Charlotte ★ 179 · commit 2026-09-11 Your AI agent burns ~50,000 characters of accessibility tree just to look at the Hacker News front page. 2,245 installs/mo · 1 release/90d · needs 1 env var $ npx -y @ticktockbent/charlotte 09 Agent402.Tools: pay-per-call web tools ★ 39 · commit 2026-09-30 Agentic Finance: 500+ agent tools, multi-chain USDC over x402 or MPP, free via PoW or card credits 2,419 installs/mo · 8 releases/90d · needs 1 env var $ npx -y agent402-mcp 10 Crawlforge MCP Server ★ 2 · commit 2026-09-30 31 web scraping, crawling, deep-research & autonomous-extraction tools for Claude, Cursor & any MCP client. 11,227 installs/mo · 10+ releases/90d · needs 12 env vars $ npx -y crawlforge-mcp-server 11 Decodo MCP Server ★ 37 · commit 2026-09-30 Connect LLMs and AI agents to live web data using MCP (Model Context Protocol). 1,578 installs/mo · 30 tools documented · needs 1 env var $ npx -y @decodo/mcp-server 12 Zenrows MCP ★ 19 · commit 2026-09-29 The Zenrows MCP (Model Context Protocol) server is the standard way AI systems use Zenrows' web data infrastructure. 2,102 installs/mo · 3 tools documented · needs 1 env var $ npx -y @zenrows/mcp 13 Exa ★ 5,058 · commit 2026-09-23 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 14 HasData Instagram ★ 16 · commit 2026-09-24 A hosted Model Context Protocol (MCP) server that gives Claude, Cursor, Windsurf and any other MCP client two read-only Instagram tools. 1,434 installs/mo · 2 tools documented · 3 releases/90d · needs 1 env var $ npx -y @hasdata/instagram-mcp 15 Jobseek ★ 200 · commit 2026-09-30 Search jobs and companies on Job Seek (jseek.co) 402 installs/mo · no env vars documented $ npx -y @jseek/mcp-server

How to choose between them

Firecrawl MCP Server tops the list - the most installs (297,906 last month) and actively maintained. 6 of these 15 offer a remote endpoint (no local process to run); the rest are local stdio servers. 3 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 297,906 installs in the last month (as of September 2026). By GitHub stars the leader is Apify MCP Server (8,922).

How many web scraping MCP servers exist?

We track 494 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 97 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 97, all of which you can see on this page. The other 397 we track have stopped being maintained, or nobody is using them yet. Full recipe: how we verify.