Browser Automation MCP Servers

MCP servers that drive real browsers — navigation, clicking, form-filling and screenshots. Each entry is scanned with the deterministic Capability-Flow Trust Model — grades are computed, never self-reported.

Peekdev Source verified npm
A
@peekdev/mcp

local-first browser-session forensics + repro for AI coding agents. peek's native messaging host + stdio MCP server — owns ~/.peek/sessions.db (better-sqlite3) and bridges the browser extension, CLI, and AI tools to one local source of truth.

Browser Automation Score 93/100 2 findings 168/wk Cap. High
Public Browser npm
A
public-browser

Public Browser MCP Server - Chrome browser automation via CDP

Browser Automation Score 93/100 4 findings 166/wk Cap. High
Apitap Core npm
A
@apitap/core

Intercept web API traffic during browsing. Generate portable skill files so AI agents can call APIs directly instead of scraping.

Browser Automation Score 93/100 5 findings 165/wk Cap. High
Chrome 4 implementations
A
best: chrome-mcp

Model Context Protocol (MCP) server for controlling Google Chrome browser on macOS. Enables AI assistants like Claude to automate Chrome via DevTools Protocol.

Browser Automation Best score 93/100 4 findings 165/wk Cap. High
Amenbo npm
A
amenbo

Skims the web without making waves — a Japanese-web-native MCP server for low-impact, token-efficient web collection: outline→section progressive disclosure and diff-only refetches keep context small

Browser Automation Score 93/100 3 findings 163/wk Cap. High
Wcag Checkr npm
A
@wcag-checkr/mcp

Model Context Protocol server for wcagcheckr. Lets LLM-IDEs (Claude Code, Cursor, Continue, etc.) drive accessibility audits, verify forensic receipts, and look up tier features programmatically. Same audit engine as the Chrome extension and CI runner.

Browser Automation Score 93/100 1 finding 142/wk Cap. High
Zen npm
A
zen-mcp

MCP server for Zen Browser automation via WebDriver BiDi

Browser Automation Score 93/100 4 findings 124/wk Cap. High
Chromecp npm
A
chromecp

Chrome MCP Server - Standalone version of mcp-chrome-bridge by hangye

Browser Automation Score 93/100 9 findings 91/wk Cap. High
Brightspace Source verified npm
A
brightspace-mcp-server

MCP server for Brightspace (D2L). Check grades, due dates, assignments, announcements, syllabus, rosters and more via Claude, ChatGPT, Cursor, Windsurf, or any MCP client.

Browser Automation Score 93/100 5 findings 87/wk Cap. High
Obscura npm
A
obscura-mcp

MCP server adapter for Obscura headless browser - high-performance web scraping with anti-detection

Browser Automation Score 93/100 13 findings 85/wk Cap. High
ThinkRun npm
A
@thinkrun/mcp

Connects AI coding agents to the user's real Chrome browser with real sessions and cookies so they can test their own frontend work.

Browser Automation Score 93/100 9 findings 84/wk Cap. High
Pixelcheck Source verified npm
A
pixelcheck

MCP-first browser primitives for AI agents — real eyes and hands on the web. Local-first. Vendor-agnostic. Yours to own.

Browser Automation Score 93/100 5 findings 74/wk Cap. High
Web Inspector npm
A
mcp-web-inspector

Web Inspector MCP: Give LLMs visual superpowers to see, debug, and test any web page.

Browser Automation Score 93/100 2 findings 74/wk Cap. High
Webpage Source verified npm
A
webpage-mcp

Webpage MCP server

Browser Automation Score 93/100 17 findings 74/wk Cap. High
Kiyas Cli Source verified npm
A
kiyas-cli

MCP server and CLI for AI-powered design fidelity — compare Figma designs (or screenshots) against rendered UI. Measured on a golden eval set: 90% mutation recall, zero false positives on clean pairs. Uses your Claude Code or Codex subscription — no API k

Browser Automation Score 93/100 4 findings 62/wk Cap. High
Leapfrog npm
A
leapfrog-mcp

Multi-session browser MCP for AI agents — 36 tools, stealth, persistent auth, code-first scripts, API sniffer, agent intelligence

Browser Automation Score 93/100 10 findings 62/wk Cap. High
Zahori npm
A
zahori

Find the media stream behind any web page. A real browser drives the player and sniffs out the HLS/DASH/MP4; an optional LLM learns tricky sites and repairs them when they change.

Browser Automation Score 93/100 2 findings 58/wk Cap. High
Selenix npm
A
@selenix/mcp-server

MCP server that bridges Claude Desktop (or any other local app supporting MCP) with Selenix for browser automation and testing. Enables creating, running, debugging, and managing browser automation tests through natural language.

Browser Automation Score 93/100 1 finding 57/wk Cap. High
Puppeteer Real Browser 2 implementations
A
best: puppeteer-real-browser-mcp-server

Detection-resistant browser automation aimed at safely driving real browsers.

Browser Automation Best score 93/100 2 findings 56/wk Cap. High
Gdocs Comments npm
A
gdocs-comments-mcp

MCP server that adds range-anchored (inline) comments to Google Docs — the one comment operation the Google Docs/Drive APIs cannot do — by driving a real logged-in Docs session with Playwright.

Browser Automation Score 93/100 1 finding 55/wk Cap. High
Glance npm
A
glance-mcp

AI-powered browser automation MCP server for Claude Code

Browser Automation Score 93/100 1 finding 55/wk Cap. High
Aidemo npm
A
@tandryukha/aidemo

AI Demo Engine — turn a storyboard into a narrated, captioned product demo video

Browser Automation Score 93/100 8 findings 54/wk Cap. High
Plasmate npm
A
plasmate-mcp

MCP server for Plasmate - the browser engine for AI agents. Use with Claude Code, Claude Desktop, Cursor, Windsurf.

Browser Automation Score 93/100 1 finding 54/wk Cap. High
Mult Fetch npm
A
@lmcc-dev/mult-fetch-mcp-server

An MCP protocol-based web content fetching tool that supports multiple modes and formats, can be integrated with AI assistants like Claude

Browser Automation Score 93/100 9 findings 52/wk Cap. High