mcpField
A
AgentKit Browser Automation

AgentKit Browser Automation

Local
github.com/tmaheshBrowser Automation2Updated 76w ago
Repository

About AgentKit Browser Automation

AgentKit Browser Automation is a browser agent built with Inngest-AgentKit and Firebase-Genkit for web navigation and task execution. It uses a separate Playwright MCP server for browser access.

Key features

  1. 01Web navigation
  2. 02Browser task execution
  3. 03Built with Inngest-AgentKit and Firebase-Genkit

Use cases

  1. 01Automating web navigation
  2. 02Executing tasks in a browser

MCP support

It uses a separately started Playwright MCP server for browser automation.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "playwright-agent": {
      "command": "npx",
      "args": [
        "-y",
        "@playwright/mcp"
      ]
    }
  }
}
Run commandnpx -y @playwright/mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@playwright/mcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

gentKit Browser Automation

A browser agent built with Inngest-AgentKit and Firebase-Genkit, featuring an agent system for intelligent web navigation and task execution.

Getting Started

Prerequisites
  • Node.js (v20 or higher)
  • npm or yarn
  • OpenAI API key (for GPT models)
  • Goolge AI key (for gemini models)
Installation
  1. Clone the repository:
git clone https://github.com/tmahesh/playwright-agent.git
cd playwright-agent
  1. Install dependencies:
npm install
  1. Set up environment variables:
cp .env.sample .env
# Edit .env with your API keys
  1. Start plawright mcp server in a seperate terminal window
npx @playwright/mcp@latest --port 8931
  1. To run with genkit sdk
npx tsx genkit.ts

#dev server(optional but recommended)
#It has fantastic observaibility built-in with opentelemetry
npx genkit start -- npx tsx --watch genkit.ts
  1. If you want to try agentkit of inngest-cli (NOTE: the names are very close agentkit nad genkit)
npx tsx agentkit.ts

#dev-server (optional)
npx inngest-cli@latest dev --no-discovery -u http://localhost:3000/api/inngest -v

Acknowledgments

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.