anti bot mcp servers

scrapfly/scrapfly-mcp

MCP server Claude CodeCodexCursor +2

Scrape any website, extract structured data, and collect web content at scale with AI agents. Runs locally from the scrapfly-mcp npm package.

MikkoParkkola/nab

MCP server Claude CodeCodexCursor +2

MCP server "nab" as configured in MikkoParkkola/nab. Launched with ${CLAUDE_PLUGIN_ROOT}/bin/nab-mcp-wrapper.

Hyper-Solutions/hypersolutions-claude-code

MCP server Claude CodeCodexCursor +2

MCP server "powhttp", hosted remotely at localhost, as configured in Hyper-Solutions/hypersolutions-claude-code.

Hyper-Solutions/hypersolutions-claude-code

MCP server Claude CodeCodexCursor +2

MCP server "har-analyzer", hosted remotely at har-mcp.hypersolutions.co, as configured in Hyper-Solutions/hypersolutions-claude-code.

andresolbach/nodriver-mcp-server

MCP server Claude CodeCodexCursor +2

Undetected Chrome automation MCP server powered by nodriver — a stealth, anti-bot-resistant alternative to chrome-devtools-mcp for Claude, Cursor and other AI agents. Runs locally from the nodriver-mcp Python package. Needs 4 environment variables to run.

Noah3521/hermes-computer-use

MCP server Claude CodeCodexCursor +2

Pixel-level browser automation MCP server for WSL2 — drive a real Chrome with screenshot + xdotool, no CDP. Runs locally from the hermes-computer-use Python package.

capad-xyz/searchts

MCP server Claude CodeCodexCursor +2

The missing layer between AI and the web. Open-source escalating unlocker (browser-fingerprinted fetch -> JS-render relay -> stealth browser) for read, keyless multi-provider search with rank fusion, subtitles-first video transcribe, and on-demand asset/design-inspiration grab (palette/fonts/assets through the same…

Goldentrii/proxy4agent

MCP server Claude CodeCodexCursor

Residential proxy MCP server for AI agents — bypass Cloudflare/Akamai, geo-target 195+ countries, sticky sessions, Google search. Works with Claude, Cursor, Windsurf. Multi-provider: Novada, BrightData, Smartproxy, Oxylabs. Runs locally from the bestproxy4agents npm package. Needs 10 environment variables to run.

ScrapeUnblocker/scrapeunblocker-mcp

MCP server Claude CodeCodexCursor

Fetch any web page's HTML or AI-parsed JSON through the ScrapeUnblocker anti-bot API. Runs locally from the scrapeunblocker-mcp npm package. Needs 1 environment variable to run.

nolindnaidoo/scrape-le

MCP server Claude CodeCodexCursor

Analyse robots.txt content and report whether a path may be crawled. Runs locally from the scrape-le-mcp npm package.

bilginerdem/craw-mcp

MCP server Claude CodeCodexCursor

MCP server "crawmcp" as configured in bilginerdem/craw-mcp. Runs locally from the crawmcp npm package.

Dutta-SD/web-fetch-mcp

MCP server Claude CodeCodexCursor

Resilient web-fetch MCP server: 3-tier escalation (curlcffi -> Patchright -> nodriver) that fails honestly, with article-extraction mode and automatic content-type handling (HTML/JSON/PDF/image). Runs locally from the web-fetch-mcp Python package.

labtoolsstudio/fetchmcp

MCP server Claude CodeCodexCursor

Drop-in fetch MCP: clean Markdown from any URL, with JS rendering and anti-bot. Runs locally from the @labtoolsstudio/fetchmcp npm package.

ProxyHatCom/HatFetch

MCP server Claude CodeCodexCursor +2

Give any LLM agent the power to read any website — even the ones that block bots. An MCP server that returns clean Markdown and handles blocks automatically via residential proxies. Runs locally from the hatfetch npm package.

virajverse/infinity-scraper

MCP server Claude CodeCodexCursor +2

MCP server "infinity-scraper" as configured in virajverse/infinity-scraper. Runs locally from the infinity-scraper Python package.