2,000+ AI tools you can run locally Add tool

Playwright MCP

An open-source browser automation MCP server gives AI agents structured page access without a vision model and runs locally or as a self-hosted service.

Playwright MCP gives AI agents browser control for testing and tasks that involve interacting with web pages. It reads structured accessibility snapshots, so agents can identify page elements without a vision model.

Page interaction: Agents can click elements, drag between targets, drop files or data onto a page, and inspect browser console messages.
Session continuity: Persistent profiles retain login information between sessions and automatically separate browser profiles by project; isolated contexts support separate testing sessions.
Existing browser sessions: A browser extension lets an agent connect to a browser session you already have open.
MCP clients: Use the server with VS Code, Cursor, Windsurf, Claude Desktop or another compatible MCP client.

The server can run locally or as a standalone self-hosted service over HTTP. Docker deployment supports headless Chromium only. It requires Node.js 18 or newer and is open source under Apache 2.0.

Only one browser instance can use a persistent profile at a time, so clients sharing a workspace can conflict. Playwright MCP doesn't provide a security boundary.

MCP Servers and Agent Skills Computer and Browser Agents macOS Windows Linux Docker Power up your coding agent Browser automation Code execution LM Studio integration MCP Tool calling

Similar to Playwright MCP

Chrome DevTools MCP

4 videos

An open-source local MCP server that lets AI coding assistants control Chrome, inspect browser errors and analyze performance through DevTools.

55.5KUpdated 1 day agoApache-2.0

#Browser automation#MCP#Tool calling

Chrome DevTools MCP connects AI coding assistants to a live Chrome browser through a locally running server. It's for developers who want an agent to investigate web app behavior alongside its coding work.

Computer and Browser AgentsMCP Servers and Agent Skills

GitHub MCP Server

9 videos

An MCP server that connects AI assistants to GitHub repositories, issues and workflows, available as a local connector or GitHub-hosted service.

34.4KUpdated 1 day agoMIT

Docker#Git integration#MCP#Tool calling

GitHub MCP Server connects compatible AI assistants to GitHub so developers can ask about code and have an assistant act on repository activity. It's GitHub's official connector for the Model Context Protocol (MCP).

MCP Servers and Agent Skills

Context7

8 videos

A locally runnable MCP server and CLI fetch version-specific docs for coding assistants from a hosted service. The server code uses the MIT license.

64.8KUpdated 2 days agoMIT

#MCP#RAG#Tool calling

Context7 is a locally runnable MCP server and CLI that connect coding assistants to its hosted documentation service. It's for developers who want library references and code examples in their assistant's context. The local component is the connection to that service: the API backend, document parsing and crawling engines remain private hosted components.

Coding Assistants and AgentsLLM Libraries and SDKsMCP Servers and Agent Skills

Browser4

A self-hosted browser automation engine that runs AI agent tasks, extracts structured web data, and supports parallel crawling on Windows, macOS, and Linux.

1.2KUpdated 3 days agoApache-2.0

macOS · Windows · Linux#Agent Skills#Batch processing#Browser automation

Browser4 is a browser automation engine for developers building AI agents, web research tools, and data collection workflows. It controls real Chrome browsers and handles interactive pages that require clicks, forms, or JavaScript before their data is accessible.

Computer and Browser AgentsMCP Servers and Agent SkillsWeb Scraping for AI

BrowserOS

A local Chromium browser lets MCP-compatible AI agents use your signed-in accounts, work in parallel tabs, and record sessions for review.

14.3KUpdated 21 hours agoAGPL-3.0

macOS · Windows · Linux#Browser automation#LLM tracing#MCP

BrowserOS neo is a secondary Chromium browser for AI agents handling web tasks that require signed-in accounts. Agents work in their own tabs while you continue browsing, with a live view of their actions.

Computer and Browser AgentsMCP Servers and Agent Skills

BrowserWing

A local browser automation tool that records reusable workflows, exports them as MCP commands or Skills, and extracts structured website data.

1.4KUpdated 3 months agoMIT

macOS · Windows · Linux · Web#Agent Skills#Browser automation#MCP

BrowserWing is a local browser automation tool for developers and AI agent users who need repeatable website tasks and structured data. It lets you record a workflow once and make it available to agents as a reusable action.

AI Workflow AutomationComputer and Browser AgentsMCP Servers and Agent SkillsWeb Scraping for AI