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 MCPMicrosoft's official Playwright-based browser automation MCP server
FMRS43 / 100 · D78 / 100 · B
Reliability3 / 2013 / 20
Security and permissions8 / 2012 / 20
Maintenance17 / 2018 / 20
Documentation9 / 2018 / 20
Setup experience6 / 2017 / 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
  • Scenarios where an AI assistant needs to actually drive a browser to complete a task
  • Web automation testing and end-to-end verification
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
  • Simple static-text scraping (a lightweight scraper is a better fit)
  • Environments sensitive to browser resource usage that can't run a full browser engine
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
  • Requires installing and running a browser engine (Chromium/Firefox/WebKit) locally or on a server
  • browser_navigate can visit any URL; browser_evaluate can run arbitrary JavaScript in the page context
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
  • browser_evaluate executing arbitrary scripts carries risk if a malicious page is visited — restrict to trusted sites or an isolated environment
  • Long-running browser instances consume significant memory and CPU
Supported clientsClaude Desktop, Claude Code, VS Code, Cursor, WindsurfClaude Desktop, Claude Code, VS Code, Cursor, Windsurf, JetBrains IDEs, Zed, Cline, Amp, Kiro, LM Studio, Antigravity, Goose
Tools010