Skip to main content
Glama
124,726 servers. Updated
Browse by product
20 Best Browser Automation MCP Servers: compared and ranked, November 2026Ranked from 5,464 matching servers on stars, growth, downloads and maintenance. Updated .

Matching MCP tools:

Matching MCP Connectors:

"Understanding and Using the Browser Console" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    A
    quality
    B
    maintenance
    Provides a stable, side-effect-free MCP tool contract that enables AI workflows to be prototyped, demoed, tested, or dry-run without connecting to databases, APIs, files, or other real data sources. It enables swapping in a real data server later without changing the AI-facing interface.
    4
    65 npm
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Gives AI agents a compact, semantic interface to the browser, returning structured page snapshots with stable element IDs instead of raw DOM. Enables agents to navigate, interact, and extract information from web pages efficiently.
    26
    33 npm
    19
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    A minimal browser debugging MCP server that monitors Chrome Console logs and executes JavaScript. 97% lighter than full DevTools alternatives, providing just 4 essential tools for efficient debugging without consuming excessive context tokens.
    4
    15 npm
    1
    Apache 2.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables coding agents to control and inspect a Chrome instance over CDP, including page listing, DOM and element inspection, element picking, JavaScript evaluation, screenshots, console capture, and network request monitoring.
    17 npm
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    MCP server that lets agents drive a browser and record every action into a replayable trace, then replay it deterministically with network request assertions. It exposes tools for navigating, clicking, filling, and verifying requests.
    -
  • F
    license
    Not graded
    quality
    B
    maintenance
    Exposes your Chrome/Edge browser as MCP tools for AI agents, enabling browser automation through a Chrome extension with 47 tools for navigation, interaction, page reading, and more.
    17 npm
    -
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI agents and MCP clients to drive real Chrome, Edge, Brave, and Firefox browsers through native automation protocols. It exposes tools for navigation, page snapshots, form filling, clicks, screenshots, console/network inspection, and tab management.
    23
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables MCP clients to open websites, capture screenshots at multiple breakpoints, and run automated design audits for issues like overflow, small tap targets, low contrast, missing alt text, tiny text, and clipped content.
    9
    1
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Enables browser automation for React Native Web applications using coordinate-based clicks to trigger RNW's gesture responder, with multi-tab management, screenshots, and persistent sessions.
    15
    11 npm
    2
    MIT
  • A
    license
    B
    quality
    D
    maintenance
    Enables AI-driven browser automation with advanced form testing, batch operations, and intelligent element extraction for MCP-compatible applications.
    14
    8 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    A local stdio MCP server that verifies an isolated WPE WebKit runtime through a network-disabled Docker acceptance test. It exposes two bounded tools for native input, DOM/text state, and PNG capture without receiving URLs, profiles, credentials, or public-web access.
    2
    Apache 2.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to control a real browser through intent-based tools—reading pages, filling forms, clicking, and replaying self-healing recipes—while returning only concise answers instead of the DOM.
    6 npm
    1
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Provides AI agents with deep visibility into a running web page's UI by capturing DOM, styles, and screenshots through a lightweight bookmarklet. It facilitates design-to-code comparisons, accessibility audits, and automated CSS debugging directly within an IDE.
    27 npm
    3
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Lets Claude Code read in-browser review comments, element removals, and text/CSS edits made on localhost dev pages, complete with selectors, HTML, React component names, source files, and screenshots. It also lets the agent claim tasks as in progress and submit solutions for the user to accept or reopen.
    1
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to drive a real Chrome instance over the Chrome DevTools Protocol — opening and navigating tabs, reading compact YAML page outlines with refs, clicking, typing, scrolling, screenshotting, and evaluating scripts — with no browser extension or installed dependencies. It also audits pages for horizontal overflow and WCAG AA contrast, available both as an MCP tool and as a CI-friendly CLI.
    15 npm
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Exposes 11 agent-native QA tools over stdio so coding agents can discover a project, analyze risk, select the smallest relevant test set, generate and dry-run tests, triage failures, propose tiered heals, analyze flakes, generate quality reports, and evaluate release readiness. Planning and healing tools stay read-only or propose-only, while execution defaults to dry-run, keeping agent actions safe and evidence-backed.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that fuses Playwright and browser-use for browser automation testing, offering 59 tools for AI-driven exploration and precise assertions on a shared browser instance, with built-in stealth anti-detection.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to drive a real headless Chrome over the DevTools Protocol without any extension, exposing tools to list, open, navigate and read tabs as compact accessible outlines with element refs, click, type, scroll, take screenshots, and inject scripts. It also runs horizontal-overflow and WCAG AA contrast audits via both an MCP tool and a CI-friendly CLI.
    15 npm
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents to automate and debug real Chromium browsers with capabilities like screenshots, video recording, performance analysis, visual regression testing, and OCR text extraction.
    13
    -
  • A
    license
    A
    quality
    C
    maintenance
    Enables AI agents and MCP hosts to drive a persistent headless Chromium browser through Playwright, navigating pages, mapping visible fields and actions, clicking, typing, scrolling, and capturing screenshots via stdio tool calls. It also powers a local AI Test Studio dashboard that generates and runs structured end-to-end test plans with assertions, per-step timing, and screenshot evidence.
    4
    1
    MIT
  • F
    license
    Not graded
    quality
    B
    maintenance
    Enables MCP clients and agents to query synthetic football match state, key moments, win probability, and player profiles, and to verify claims and on-screen overlay numbers against match state.
    -
  • F
    license
    Not graded
    quality
    D
    maintenance
    Enables automated browser testing of web applications using Playwright, supporting user interactions, form submissions, console monitoring, network request inspection, and visual verification through screenshots.
    -
  • A
    license
    Not graded
    quality
    B
    maintenance
    Validates .mcp.json and claude_desktop_config files to catch duplicate server names, missing binaries, invalid environment variables, and unreachable endpoints. Reports each problem along with how to fix it, so silently failing MCP servers can be diagnosed and repaired.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to drive real Chrome or Edge browsers through MCP, allowing them to open pages, interact with elements, inspect network activity, take screenshots, and record or replay flows as tests.
    7
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to safely run test suites over MCP, returning concise JUnit-based results, trimmed tracebacks, rerun-failed support, and flaky-test detection while handling timeouts, process cleanup, and bounded output.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables MCP clients to review Ceramic and ordinary websites with desktop/mobile browser QA, deterministic design and accessibility checks, optional visual judgement, and repeatable fix verification backed by preserved screenshots and reports.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    A production-oriented reliability, benchmarking, and evaluation system that layers multi-version protocol negotiation, adaptive streaming, connection pooling, and resilience onto an MCP agent runtime.
    3
    Apache 2.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables an AI to statically lint Dockerfiles and compose files without Docker by parsing their true structure, reporting line-numbered findings with concrete fixes, and analyzing cache order, .dockerignore matching, and safe fix previews as diffs.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables agents to lint OpenAPI specifications and detect breaking changes between two versions of an API, normalising Swagger 2.0 and OpenAPI 3.0/3.1 into a single model with safe $ref resolution. It exposes schema-walking and example-validation tools over stdio, classifying each change as breaking, potentially breaking, or safe based on request-versus-response variance.
    1
    MIT