Browser Automation
This MCP server provides browser automation capabilities through a browser extension and WebSocket-based communication, enabling AI assistants to interact with web pages in real-time. Built by Diamond-IT-615 using TypeScript with a monorepo structure containing a WXT-based browser extension, Node.js server, and shared types, it offers tools for extracting page content as markdown using Mozilla Readability, injecting custom CSS styles for visual modifications, retrieving current page URLs, and searching browser history with optional permissions. The implementation features a React-based popup interface for permission management, WebSocket communication on localhost:11223 for real-time browser interaction, automatic connection retry logic, and support for Chrome, Edge, and Firefox browsers, making it valuable for web scraping workflows, automated testing scenarios, content analysis tasks, and building AI assistants that need direct access to browser state and content without manual navigation.
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 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · 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/diamond-it-615/browser-mcp
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
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.