Browser Automation MCP servers

Hosted public-page screenshots and PDFs with guarded Chromium and inline MCP artifacts.

MCP server for KiteGhost — gives an agent a real Chrome browser, already signed in, on the user's own machine

Scrape any company's Lever job board and get clean, de-duplicated job data: title, team, location…

Compliance lint for AI, scraping, and privacy law. Cited findings in 200 or more jurisdictions.

Compliance lint for AI, scraping, and privacy law. Cited findings in 200 or more jurisdictions.

Official Livescraper connector for Claude and other MCP clients — create Google Maps, Reviews and Email scraping tasks straight from your AI assistant.

Ultra-lightweight local MCP bridge connecting AI software (Claude Desktop, Cursor) to TrustTalk browser inbox session

AI-native browser for agents. 71 tools with self-healing, semantic extraction, vault CLI.

Scrape, crawl and search the web for AI agents via MCP.

Compliant PDFs (PDF/A-2A + PDF/UA-1) from markdown or a compact DSL - fast, no headless browser.

Scrape Mastodon posts, profiles, hashtags and instance timelines across the fediverse. Pay per row.

One shared HTTP MCP server that lets any number of Claude Code sessions edit a live PlayCanvas Editor tab through a Chrome extension bridge, including reading/downloading and replacing a project's asset files via the PlayCanvas REST API. Every session con

125+ browser tools for PDF, Image, Video, Audio, AI, Scanner. Files never leave your device.

Headless local context engine and CLI to map codebase dependencies for AI consumption.

MCP server for Mint — AI-powered QA that runs your app in a real browser on every PR.

Model Context Protocol (MCP) server for FireScraper. Give Claude, Cursor, Windsurf, and any MCP-compatible AI agent the ability to crawl websites and turn them into clean, LLM-ready text.

Free SEO, GEO, and AEO audits: analyze any page or domain, AI-crawler access, agent readiness.

MCP server that hands your Notepix browser annotations (and their screenshots) straight to an AI coding agent.

Browser-based IDE + AI agent orchestration CLI. Run Claude Code in parallel across git worktrees, auto-approve safe tools with the Security Bouncer, and control long-running AI work from any device at app.mstro.app.

让 AI 与 Chrome 浏览器实时交互：获取历史请求、控制台日志、RUM/埋点事件，并动态设置 Mock 数据。

Live web research with related queries, browser-rendered sources, images, and evidence.

MuseScore for Claude — search sheet music and read score metadata via your signed-in browser

Your own cloud computer run by an AI agent: signed-in browser, its own email, files, long jobs.

Audit webpage access for AI crawlers. API key and Premium or Partner plan required.

30+ web-access and AI APIs behind one key: search, scraping, browsers, voice, OCR and LLMs.

Spatial DOM maps for AI agent browser navigation with anti-bot stealth.

8-tool AI web intelligence suite: search, scrape, screenshot, SEO, docs, crypto, code.

MCP Server for NEXT Finance ERP (finance.net.br) — browser login, wallets, accounts, transactions.

Agentic OS MCP Server — 150+ tools with on-demand loading (26 core), Streamable HTTP transport, background task engine, browser automation, TF-IDF semantic memory, multi-agent orchestration. Zero API keys.

Secure AI access to Windows, macOS, Linux computers and a hosted Cloud Browser.

Search, scrape, and crawl the web for AI agents. Batch scraping and answers with citations.

MCP server for 500+ pay-per-call web scraping, search, social, business, and financial data tools.

Verified business OSS MCP for search, RSS, crawling, documents, browser, media and transcription.

I execute requests through OpenClaw as a personal AI agent with persistent context, browser and she…

Scrape any Open Collective's public expenses and transactions as clean JSON — amounts, dates…

Scrape openFDA drug recalls, enforcement reports, labels and adverse events. Pay per row.

Autonomous cloud agent tasks: real browser + your tools, structured evidence-backed results.

Convert HTML or URLs to PDF documents powered by Playwright

Web scraping runtime for agents: parsers, scrapes, batches, crons, and SQL databases.

Telegram/VK audience scraping, marketplaces, Russian government registers. Free open dataset.

Give AI agents clean, LLM-ready web data — scrape any URL to markdown or extract structured JSON.

Search Perplexity using your browser login. Returns answers, sources, and thread URLs. No API key.

Phenomenal MCP bridge — connects a stdio-only MCP client to the Phenomenal MCP server over Streamable HTTP, with browser sign-in.

macOS desktop control for Claude: click, type, screenshot, AX tree, browser control, agentic loops.

Scrape any company's Pinpoint job board in one click.

MCP server connector for Pinterest — search pins, manage boards, save pins, and follow users via Playwright browser automation

Headless browser primitives for AI agents when sites need real JS rendering.

MCP server providing Playwright test generation wizard with intelligent prompts and best practices