M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionPlaywright MCPGive AI agents full browser control via structured accessibility snapshotsPlaywright MCP ServerPlaywright-based browser automation MCP server
FMRS43 / 100 · D66 / 100 · C
Reliability3 / 209 / 20
Security and permissions8 / 2011 / 20
Maintenance17 / 2015 / 20
Documentation9 / 2017 / 20
Setup experience6 / 2014 / 20
Best for
  • Users who want an LLM to drive open-ended browser tasks
  • Developers already using MCP-capable clients like Claude Desktop, VS Code, Cursor, or Windsurf
  • Cross-browser (Chromium/Firefox/WebKit) automation without hand-writing test scripts
  • Developers who need browser automation from Claude Desktop, VS Code, and similar clients
  • Users doing web testing and scraping
Not for
  • Teams needing a full end-to-end test runner with parallel execution and trace viewer — the README points to Playwright Test for that instead
  • Coding-agent setups that prioritize token efficiency and want to avoid loading large tool schemas and accessibility trees — the README recommends the lighter-weight Playwright CLI for that case
  • Environments requiring strict isolation from real browser sessions, cookies, or local files, since the agent gets genuine browser control
  • Environments requiring strict sandboxing that disallow AI-controlled browsers
  • Claude Desktop users needing HTTP/SSE mode (Claude Desktop currently requires stdio mode)
Required permissions
  • Local Node.js/npx runtime to launch the server process
  • Ability to download and run Chromium/Firefox/WebKit browser binaries
  • Outbound network access to load whatever pages the agent is directed to visit
  • Runs real browsers (Chromium, Firefox, WebKit) locally
  • Automatically downloads and installs browser binaries on first use
  • Writes log files to ~/playwright-mcp-server.log
  • Binds a local port in HTTP mode (default 8931)
Risks and side effects
  • The server grants agents real control of a browser, so a manipulated prompt could cause navigation to or submission of data on unintended sites
  • If a saved storage state (login session) is loaded, the agent may gain access to authenticated account data
  • The README does not describe any authentication or access-control mechanism built into the MCP server itself — safety depends on the host client and how target URLs are constrained
  • AI can execute JavaScript in a real browser, potentially accessing and manipulating sensitive web content
  • Automatic browser downloads consume disk space and bandwidth
  • HTTP mode binds to localhost only; exposing it via SSH tunnels still requires caution
Supported clientsClaude Desktop, Claude Code, VS Code, Cursor, WindsurfClaude Desktop, Claude Code, Cline, Cursor, VS Code
Tools01