
Browser Agent
Connects Claude to a live Chrome browser session through a WebSocket bridge and extension. Instead of dumping the entire DOM into context after every action, it sends a stripped down HTML snapshot that keeps text and interactive elements but drops the bloat. You install the extension, point it at an LLM (they recommend Gemini Flash), and invoke the browser-agent tool with a natural language prompt like "search for MCP protocol on Google." Good fallback when a site doesn't have a dedicated MCP server. Runs locally in your browser, no remote calls except to your LLM provider. The extension listens on port 9003 and executes whatever automation task you throw at it.
- GitHub stars
- 3
- tool
- 1
- transport
- STDIO
- last updated
- Oct 19, 2026
Tools
1 toolsPublic tool metadata for what this MCP can expose to an agent.
browser-agentRun a task in Chrome browser with AI and automation capabilities.
Run a task in Chrome browser with AI and automation capabilities.
No parameter schema in public metadata yet.
Sponsors
Readme
Runbook AI MCP Server
An MCP (Model Context Protocol) server that provides browser automation capabilities through a Chrome extension. It allows terminal-based agents like Claude Code to interact with any website through your live browser session.
Part of the Runbook AI ecosystem. Join the Discord community to provide your feedback and get involved in the development!
https://github.com/user-attachments/assets/a43fba64-bc40-4ef6-9840-e100203e2cf5
Why Runbook AI?
Most browser-based MCP tools (like chrome-devtools-mcp) blow up your LLM context window by sending the entire DOM after every browser action.
Runbook AI is different:
Details
- Repository
- github.com/runbook-ai/runbook-ai-mcp
- Categories
- Web & Browser Automation, AI & LLM Tools, Automation & Workflows
- Package
runbook-ai-mcp- Transport
- STDIO
- Registry
- MCP registry, active