Skip to content

MCP servers for browser automation

21 MCP servers that let AI control a web browser to navigate pages, fill in forms, take screenshots and scrape content. Each one shows how to install it in Claude, Cursor and VS Code, whether it runs locally or remotely, and the tools it provides.
  1. Browser agents and cloud browsers for AI, with an MCP server for web tasks

    • 7 tools
    • Remote
    • Freemium
    • 121K GitHub stars
    • Browser automation
  2. Persistent memory for Claude Code, Codex and OpenCode, stored in SQLite on your machine

    Runs locally
    • Open source
    • Knowledge and memory
  3. Give an assistant a cloud browser to scrape, search, crawl and audit pages

    • 5 tools
    • Remote
    • Freemium
    • Browser automation
  4. Turns websites into typed JSON tool calls that agents can search, read, log in and act on

    Not checked yet
    • 5 tools
    • Remote
    • Freemium
    • Browser automation
  5. Persistent Linux cloud desktops that an agent can see, click, type into and run tasks on

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • Cloud and infrastructure
  6. Cloud Android phones an AI agent can see, tap and drive, or hand a task in plain words

    Not checked yet
    • 9 tools
    • Remote
    • Freemium
    • Browser automation
  7. Run 56 web performance snippets in headless Chromium and read Core Web Vitals results

    Runs locally
    • 1 tool
    • Open source
    • Browser automation
  8. Build, run, test and submit browser extensions to four stores from your AI agent

    Not checked yet
    • 2 tools
    • Remote
    • Freemium
    • Developer tools
  9. Assistant that drives Chrome or Edge via a browser extension, asking before key actions

    Runs locally
    • Free
    • Browser automation
  10. Local MCP server for browser control and session recording for coding agents

    Runs locally
    • Freemium
    • Browser automation
  11. Verify a running web app from inside: look, act, observe and assert, without screenshots

    Runs locally
    • 10 tools
    • Open source
    • Developer tools
  12. Supervised cloud browser where an agent drives and a human can watch and take over

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • Browser automation
  13. Puts browser and dev-server logs on one clock so agents can match errors to stack traces

    Runs locally
    • 11 tools
    • Free
    • Developer tools
  14. Let an AI agent drive Android, iOS, TV and web apps, and save the steps as test suites

    Runs locally
    • 2 tools
    • Open source
    • Developer tools
  15. Read-only Playwright CI results for agents: new versus known failures and flaky tests

    Runs locally
    • Freemium
    • Browser automation
  16. Turns websites into callable tools so agents skip the browser, with a cloud fallback

    Not checked yet
    • Remote
    • Freemium
    • Web search and scraping
  17. Approve agent actions from your phone; sandboxed browser vault with saved logins

    Runs locally
    • Free
    • Security
  18. Turns websites and signed-in accounts into callable APIs, run in the cloud or locally

    Not checked yet
    • 3 tools
    • Remote
    • Freemium
    • Web search and scraping
  19. Launch and check mobile device simulations from an AI agent in your editor

    Not checked yet
    • Remote
    • Freemium
    • Developer tools
  20. Browser API as agent tools: Markdown, screenshots, structured data, automation, crawls

    Runs locally
    • 10 tools
    • Freemium
    • Web search and scraping

See every kind of AI for browser automation: tools, agents, MCP servers and skills.Ranked: the best AI for browser automation.