agent-infra/mcp-server-browser
Overview
A browser automation tool using Puppeteer, supporting local and remote browser connections. Features include natural language control via Vision-Language Models, visual recognition, and cross-platform support.
Capabilities
- • tool call interface
- • browser automation integration
- • github integration
- • workflow automation support
Best For
MCP server tool for browser automation with Puppeteer, supporting local/remote connections and natural language control via Vision-Language Models (VLM).
Decision Snapshot
Install
available
Usage
available
Docs
8 links
Capabilities
4 key capabilities detected
- • GitHub stars: 29414
- • Forks: 2882
- • Source provenance count: 3
- • Active signal: Updated this week from lifecycle signals.
- • Last seen: 4/15/2026
- • Published: 3/16/2026
Installation / Setup
# Launch with `npx`. && npx @agent-tars/cli@latest && # Install globally, required Node.js >= 22 && npm install @agent-tars/cli@latest -g
Usage
# Launch with `npx`. && npx @agent-tars/cli@latest && # Install globally, required Node.js >= 22 && npm install @agent-tars/cli@latest -g
Features
- • 🖱️ **One-Click Out-of-the-box CLI** - Supports both **headful** Web UI and **headless** server execution.
- • 🌐 **Hybrid Browser Agent** - Control browsers using GUI Agent, DOM, or a hybrid strategy.
- • 🔄 **Event Stream** - Protocol-driven Event Stream drives Context Engineering and Agent UI.
- • 🤖 Natural language control powered by Vision-Language Model
- • 🖥️ Screenshot and visual recognition support
- • 🎯 Precise mouse and keyboard control
- • 💻 Cross-platform support (Windows/MacOS/Browser)
- • 🔄 Real-time feedback and status display
Use Cases
- • Supports capabilities such as: tool call interface; browser automation integration; github integration.
- • Common usage themes: agent, agent-tars, browser-use, computer-use.
Supported Clients / Integrations
- • tool call interface
- • browser automation integration
- • github integration
- • workflow automation support
Compatibility Signals
- • GitHub: supports (Detected in parser config/capability hints.)
Prompt Examples
example
• # Launch with `npx`. && npx @agent-tars/cli@latest && # Install globally, required Node.js >= 22 && npm install @agent-tars/cli@latest -g
Notes / Requirements
- • Primary language: TypeScript/JavaScript
- • License: Apache-2.0
- • Documentation coverage: high
- • Parser coverage score: 1.00
- • Source provenance includes GitHub discovery
- • Source feeds: Awesome MCP Servers (punkpeye), GitHub Search API
- • Topic cluster: data-infra
Official Links
Source Information
You can verify all information on this page against the source repository above.
Related MCP Tools
@rolexjs/mcp-server
MCP server for Rolex that exposes RDD role management as MCP tools.
zero-config-cli-bridge
A zero-configuration tool to expose local authenticated CLIs as MCP tools without setup or API keys.
@williamp29/project-mcp-server
A ModelContextProtocol (MCP) server enabling agents to discover project resources, including OpenAPI-based APIs and database schemas.
@upstash/context7-mcp
Context7 is a specialized MCP server that provides extended context management for AI assistants. It maintains conversation context across long sessions, enabling AI models to reason about complex, multi-turn interactions without losing track of earlier exchanges. Editor's Review: Context7 solves a fundamental problem with LLM-based AI assistants—limited context windows. By intelligently managing what context to retain and how to retrieve it, Context7 enables AI assistants to maintain coherence over much longer interactions than would otherwise be possible. This is particularly valuable for complex debugging sessions, architectural design discussions, or any workflow where earlier decisions inform later ones. The server is well-documented and straightforward to configure. If you find that AI assistants lose track of your project details in long sessions, Context7 is one of the most practical solutions available.
What To Do Next
Continue from this tool into a workflow and a learn guide to shorten implementation time.