- Scrapeless @scrapeless-ai/scrapeless-mcp-serverWeb search, browser automation, scraping, crawling and CAPTCHA solving for AI agents.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.169 GitHub stars.
- Oxylabs @oxylabs/oxylabs-mcpFetch and process content from specified URLs & sources using the Oxylabs Web Scraper API.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.104 GitHub stars.
- Oxylabs @smithery/oxylabs-oxylabs-mcpFetch and process content from specified URLs using the Oxylabs Web Scraper API.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.104 GitHub stars.
- gtm-api: LinkedIn MCP Server @gtm-api/linkedin-mcpManaged LinkedIn MCP server for AI agents: search, connect, message and enrich on accounts you own.18% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.89 GitHub stars.
- ShadowCrawl @devshero/shadow-crawlStealth scraping & search. Bypasses Cloudflare, DataDome & LinkedIn via Cyborg HITL approach.51% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.70 GitHub stars.
- TesterArmy @tester-army/testerarmyAgents that test your web and mobile app like real users, on every pull request.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.68 GitHub stars.
- Computer-Use Agents API @hcompai/hai-agentsRun and manage H Company's Computer-Use Agents from any MCP client.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.42 GitHub stars.
- Aginx Browser @aginx/aginxbrowserStealth web browser for agents: search, fetch, click, download and type in persistent MCP sessions.23% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.38 GitHub stars.
- KERNEL @onkernel/kernel-mcp-serverAccess Kernel's cloud-based browsers and app actions via MCP (remote HTTP + OAuth).8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.37 GitHub stars.
- Ausca @ausca/agent-servicesPay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.36 GitHub stars.
- Zenrows @zenrows/zenrows-mcpZenrows MCP server — Fetch, Extract, Batch, and Browser Sessions for AI coding assistants11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.19 GitHub stars.
- Tap @leonting1010/tapBrowser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.18 GitHub stars.
- E2LLM @e2llm/element-to-llmE2LLM gives your AI eyes and hands in a real browser: structured perception (SiFR) plus action.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.7 GitHub stars.
- Anybrowse @kc23go/anybrowseConverts any URL to clean, LLM-ready Markdown using real Chrome browsers9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.5 GitHub stars.
- webEmbedding @jongko54/web-embeddingSource-first URL clone, capture, rebuild, and fidelity verification tools.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.5 GitHub stars.
- FourA @foura/mcpReliable web access for AI agents: smart HTTP, rotating proxies, and full-browser rendering.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.4 GitHub stars.
- Screen Browser @screenbrowser/screenbrowserNarrated demo and tutorial videos of your web app, from a guide or your coding agent.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.3 GitHub stars.
- Novada @novadalabs/novada-mcpSearch, extract, crawl, map, research, scrape 16 platforms, browser automation, proxy — one API key.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.3 GitHub stars.
- Arch Tools @deesmo/arch-tools-mcp63 production tools for AI agents — one API key, pay per call in USDC (x402) or Stripe credits.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.3 GitHub stars.
- Gateway @wingmanprotocol/gatewayDurable self for AI agents: one-call resume, memory, real browser, free chat + hire real humans.15% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.3 GitHub stars.
- Tools for Agents @max124vip-dev/tools-for-agentsDecision Layer for AI Agents — 58+ tools, Advisor, MCP. Free key: POST /v1/register {}.16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
Browser automation MCP servers
A server here drives a real web browser to navigate, click and fill in forms.
Not here: extracting pages without a browser.
159 remote418 localTagged by Odel's AI, which can make mistakes
Most popular in Browser automation
By GitHub stars, at most two per publisher- Number 1: Skyvern@skyvern-ai/skyvernAI-powered browser automation — navigate, click, fill forms, and extract data from any website.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.23,168 GitHub stars.
- Number 2: Browserbase@smithery/browserbasehq-mcp-browserbaseProvides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to i…10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.3,405 GitHub stars.
- Number 3: Oya Browser@oyadotai/oya-browserReal Chrome for agents: start a browser, read pages as numbered markdown, click, type, hand off.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.349 GitHub stars.
