AI-powered browser automation MCP server for Claude Code. Navigate, click, screenshot, test — all from your terminal.
Glance is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo view DebugBase/glance --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
Glance gives Claude Code a real browser to see and interact with web apps. You can ask Claude to test login flows, take screenshots, or check pages — all from your terminal. It uses Playwright under the hood to control the browser.
Glance is an MCP server that integrates with Claude Code to provide real browser automation capabilities. It offers 30 MCP tools for complete browser control, including navigation, clicking, typing, screenshots, accessibility snapshots, and test scenario execution. Key features include inline screenshots so Claude can see what the browser sees, accessibility snapshots for full page structure as text, a test scenario runner for defining multi-step tests in JSON, 12 assertion types, session recording and replay, visual regression testing with pixel-level comparison, network and console monitoring, security controls like URL allowlists/denylists and rate limiting, and headed mode for real-time browser observation. Glance is built on Playwright and is designed for developers who want to automate browser interactions through natural language commands in Claude Code.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 102 days ago.
151 GitHub stars indicate community interest.
5 open issues signal maintenance load.
MIT license detected.
Test login flows and form submissions on localhost or staging environments
Take screenshots of web pages for documentation or visual verification
Run end-to-end test scenarios defined in JSON
Monitor network requests and console errors during development
Perform visual regression testing by comparing screenshots
Running arbitrary JavaScript in the browser can be a security risk; use URL allowlists and JS execution policies
Screenshots may capture sensitive data; ensure proper access controls
Network monitoring can expose internal endpoints; restrict to trusted environments
151
Stars
23
Forks
5
Issues
MIT
License
Framework for building agents that run in the browser, built for Angular and React.
Browser automation CLI built for AI agents — breaks anti-bot walls, supports multi-session parallel execution.
Anti-detection browser server for AI agents with C++ engine-level fingerprint spoofing.
AI-powered browser automation MCP server for Claude Code. Navigate, click, screenshot, test — all from your terminal.
Web developers who want to automate browser testing via Claude Code, QA engineers looking for AI-assisted end-to-end testing, DevOps engineers integrating browser checks into CI/CD pipelines
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Running arbitrary JavaScript in the browser can be a security risk; use URL allowlists and JS execution policies Screenshots may capture sensitive data; ensure proper access controls
Similar or complementary options to evaluate include hashbrown, Browser Act Skills, camofox-browser.
Jun 6, 2026
3 security/trust notes recorded.
Setup difficulty is 2/5.