Skip to main content
Glama
Sign In
Playwright MCP

Playwright MCP

by dev-larrykw
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

Related Servers

Alternatives to Playwright MCP

No user-submitted related servers found.

    Related Servers

    • aa-browser

      yuchen0x1
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to drive a full Chromium desktop browser over MCP by reading structured accessibility-tree snapshots with stable element refs and token-saving incremental updates, then navigating, clicking, typing, selecting, scrolling, and extracting page text. It also supports tab management, console logs, screenshots, and HTTP traffic capture with request/response bodies and HAR export for API inspection.
      1
      MIT

    • Playwright MCP

      zhangjia2024
      A
      license
      B
      quality
      B
      maintenance
      Provides browser automation capabilities so LLMs can interact with web pages through structured accessibility snapshots, without needing screenshots or vision models. It offers fast, lightweight, and deterministic tool application for driving browsers via structured data.
      25
      10,630,264 npm
      Apache 2.0

    • Web Bridge

      JohnXu22786
      A
      license
      A
      quality
      C
      maintenance
      Browser automation MCP server that uses a real browser to give agents eyes and hands—open pages, click, fill, screenshot, and run scripts via accessibility-tree snapshots.
      22
      26 npm
      MIT

    • zimreaper

      Mr-Destroyer
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to drive a real Chromium browser over MCP using genuine mouse, keyboard, and wheel input, with accessibility snapshots, diffs, network logs, forked sessions, and replayable traces for bug bounty hunting.
      20
      MIT

    • agbrowser

      neko233-com
      A
      license
      Not graded
      quality
      B
      maintenance
      MCP server that lets AI agents drive the locally installed Chrome or Edge, opening pages, taking compact accessibility-tree snapshots with @e references, and clicking, typing, scrolling, or capturing screenshots. It also exposes multi-account and cross-channel tab switching, tab sync rules, and ad-block/perf statistics.
      MIT
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.3/5.0

    Scored across 25 tools

    Disambiguation4/5

    Most tools have clearly distinct browser-automation purposes, but a few boundaries blur: browser_close vs. browser_tabs can both close tabs, and browser_evaluate vs. browser_run_code_unsafe both execute code in different contexts. The descriptions usually clarify these differences, though an agent may still hesitate in edge cases.

    Naming Consistency5/5

    All tool names use a consistent browser_ prefix followed by snake_case verbs or noun phrases. The pattern is predictable throughout the set.

    Tool Count3/5

    25 tools is at the heavy end for a browser automation server; while most operations are genuinely useful, the surface feels granular and borderline overloaded. A more compact set could combine several low-level controls without losing capability.

    Completeness4/5

    The surface covers navigation, interaction, forms, screenshots, snapshots, tabs, dialogs, uploads, network/console inspection, and code execution. Minor gaps exist, such as explicit forward navigation/reload and cookie/storage management, but agents can often work around them with evaluate or run_code_unsafe.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data

    Resources