chrome-bridge
68GoodBorrow a tab from your own logged-in Chrome, hand it back; 2FA and CAPTCHA stay yours. 67 tools.
Loading the directory
MCP servers that control Chromium, Firefox, or a hosted browser so an agent can click, type, screenshot, and extract structured data.
587 servers
Borrow a tab from your own logged-in Chrome, hand it back; 2FA and CAPTCHA stay yours. 67 tools.
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
Build, run, inspect, and publish browser extensions from any MCP client. 34 tools, 13 browsers.
Claude steers live music by writing Strudel code played in a browser page
Capture website screenshots (viewport or full page) with your installed Chrome. Runs locally.
Technical SEO in Claude: GSC + crawl + DataForSEO - audit, market sizing, content recon.
Real Chrome for agents: start a browser, read pages as numbered markdown, click, type, hand off.
Browser MCP server: budgeted page reads, honest unread accounting, structured extraction.
Paid plans, licences, subscriptions and the paywall for Chrome extensions, on your own Stripe.
Use this MCP server to Common Crawl index discovery for historical web captures. Tools include...
Visible Electron browser driven by a semantic accessibility tree: 17 MCP tools, no screenshots.
LinkedIn for AI agents from your own Chrome session: search, profiles, lists, outreach queue.
Zenrows MCP server — Fetch, Extract, Batch, and Browser Sessions for AI coding assistants
Browser automation for MCP clients via Zen Browser. Parallel multi-tab, content extraction.
Revision-bound quality planning, execution, evidence, proof, and Playwright authoring.
Read Bilibili, Douyin, Xiaohongshu and any web page via your own logged-in Chrome.
Accessibility-tree browser for AI agents: read pages, log in, extract data, run tasks.
Read and manage your WhatsApp conversations through the KaptionAI browser extension.
Read, crawl and act on websites, signed in as the user, and turn any site into an API.
Drive your real Chrome over MCP: real logins and cookies, multi-tab automation, deny-all by default.
Browser-local and CLI static evidence for deployed AI model artifacts.
Read-only Playwright CI results for agents: new vs known failures, flaky tests, test history.
Resumable browser, API and MCP workflows for AI agents. Verify CSV/Excel batches locally.
Fetch your own Delhaize (Belgium) till receipts and weekly promotions with a headless browser.