Visit Jev Ultrafast McpHand the browser work off: an MCP server where a decision model drives the page for your agent, so a flow costs one tool call instead of a turn per click. Ref-based element tables, code-checked assertions, zero-model macro replay. Speaks CDP to your Chrome.
About Jev Ultrafast Mcp
This is an MCP server that lets an agent hand a whole browser task to the server, which drives a Chromium-family browser over the Chrome DevTools Protocol. The README says a decision model on the server picks page elements step by step, so the agent makes one call instead of one per click. The project is maintained by the GitHub account jiawei686 and describes itself as independent, not affiliated with the projects that inspired it.
The README lists ten tools, including opening a page and returning an element table, observing changes, running batches of clicks and typing, deterministic assertions, recording macros that replay without model calls, and a goal tool for full tasks. It needs Python 3.10 or newer and a Chromium-based browser. Only the goal tool needs a decision-model key, from TypeSafe or OpenRouter. It can be installed from PyPI or from a clone, and an installer script writes client configs. The licence is MIT. Performance figures in the README are the project's own claims.
Key features
- Open pages and return an element table
- Batch click, type and select actions
- Deterministic page assertions
- Record and replay macros
- Goal tool that delegates a whole task
More browser & scraping MCP servers
- Browser & scraping

Fetch MCP Server
modelcontextprotocol
A Model Context Protocol server that provides web content fetching capabilities. This server enables LLMs to retrieve and process content from web pages, converting HTML to markdown for easier consumption.
92K GitHub stars - Browser & scraping

Chrome DevTools MCP
ChromeDevTools
Chrome DevTools for agents (chrome-devtools-mcp) lets your coding agent (such as Antigravity, Claude, Cursor or Copilot) control and inspect a live Chrome browser.
57K GitHub starsTypeScriptApache-2.0 - Browser & scraping

Apify MCP Server
apify
The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and automation tools available
16K GitHub starsTypeScriptMIT - Browser & scraping

Firecrawl MCP Server
firecrawl
Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
7.8K GitHub starsJavaScriptMIT - Browser & scraping

mcp-playwright
executeautomation
The Playwright MCP Server provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages, take screenshots, generate test code, and execute JavaScript in a real browser environment.
5.7K GitHub starsTypeScriptMIT - Browser & scraping

mcp-server-browserbase
browserbase
The MCP Server provides cloud browser automation capabilities using Browserbase and Stagehand. It enables LLMs (Large Language Models) to interact with web pages, extract information, and perform automated actions, makin
3.4K GitHub starsTypeScriptApache-2.0