
bad-ass-mcp
MCP serverDesktop GUI automation through accessibility trees, with replayable tests
Runs locally- 16 tools
- Open source
- Developer tools

Desktop GUI automation through accessibility trees, with replayable tests
Runs locallyLet an agent read Safari history, tabs and reading list, with writes switched off
Runs locally
MCP server that drives your real Chrome in per-agent background tabs on Windows
Runs locallyCapture browser flows into reviewable Java tests and diagnose failures from evidence
Runs locallyMCP server that lets an assistant operate any VNC-reachable desktop by screenshot
Runs locallyBrowser automation over raw CDP in one Python file, with an MCP server for AI agents
Runs locallyBrowser MCP that records website routes and replays them without model calls
Runs locallyRun 56 web performance snippets in headless Chromium and read Core Web Vitals results
Runs locally
Finds why Playwright tests fail, proposes fixes and verifies them before keeping the edit
Runs locallyRun your agent CLI in your real, signed-in browser from a side panel or over MCP
Runs locallyMCP server that clones a web page from its URL into a verified offline HTML copy
Not checked yetBrowse login-protected and JavaScript-heavy pages through your own Chrome, Edge or Brave
Runs locallyAccessibility-tree desktop control for coding agents on macOS, Windows and Linux
Runs locally
Let an agent drive your logged-in Chrome, then replay the compiled task at zero tokens
Not checked yet
Self-hosted fleet of persistent, logged-in stealth Chrome sessions for AI agents
Runs locallyLet AI agents use the Chrome you are already signed into, with a domain allowlist
Runs locallyChrome extension plus MCP server so coding agents can use your signed-in Chrome profiles
Not checked yetHeadless Metabase MCP server using an API key, with 187 tools and read-only mode
Runs locallyCompare two logged-in identities to surface broken access control and IDOR
Runs locallyOne MCP proxy for Playwright, Figma, DevTools, Shopify Dev and Context7, with less output
Runs locallyLet an AI assistant operate Java Swing and JavaFX desktop apps with no API needed
Runs locallyRun eight-view mobile checks on AI-generated web pages and get repair-ready evidence
Runs locally
Let an AI agent work visibly in your signed-in Chromium browser, locally, with audit
Runs locallyLet Claude Code, Cursor and Codex drive your own signed-in Chrome, with human fallback
Runs locallyVerify a running web app from inside: look, act, observe and assert, without screenshots
Runs locallyRust browser automation over native webviews, for agents (MCP) and scripts
Runs locallyGives an AI agent your real Chrome through compact text snapshots and a visible cursor
Runs locallyLet a coding agent read QA Wrap browser test sessions and failures, locally
Runs locallyGive coding agents their own background tabs in your signed-in Chrome
Runs locallyCapture website screenshots with local Chrome from a CLI or an AI agent
Not checked yet