Browser
MCP Browser provides a headless browser interface for AI agents to test and analyze frontend applications in real browser environments. Built with Playwright and FastAPI, it enables AI to capture screenshots, extract DOM structures, analyze CSS properties, test accessibility, and verify responsive designs across different viewports. The implementation features a WebSocket event subscription system for real-time browser events, Docker containerization with security controls (AppArmor profiles, non-root execution), and one-command deployment for Mac Mini setups. Particularly valuable for AI coding agents that need to identify visual rendering issues and frontend problems without excessive resource usage.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/neoforge-dev/mcp-browser
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Browser from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp --scope user for --scope project to commit it to .mcp.json.