Browser Automation
Browser MCP provides programmatic control over Chrome browser instances through a Chrome extension and WebSocket-based MCP server architecture. The implementation consists of a Python WebSocket server that communicates with a Chrome extension, enabling AI assistants to perform browser automation tasks including navigation, element interaction, form filling, screenshot capture, content extraction, history/bookmark management, and console monitoring. Built with TypeScript for the extension and Python with the MCP SDK for the server, it uses content script injection for reliable page interaction and supports both isolated and main world JavaScript execution contexts. Designed for AI agents that need to interact with web applications, perform web scraping, automate testing workflows, or extract structured data from websites without requiring headless browser setups or complex automation frameworks.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- browser-automation
- Source
- PulseMCP
- Repository
- github.com/hihuzhen/browser-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Browser Automation 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.