MCP.so
Sign In

AgentKit Browser Automation MCP Server

@tmahesh

Basic information

Category

Browser Automation

Transports

stdio

Author

tmahesh

About AgentKit Browser Automation MCP Server

agentkit for playwright-mcp server

AgentKit Browser Automation MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "playwright-agent": {
      "command": "npx",
      "args": [
        "@playwright/mcp@latest",
        "--port",
        "8931"
      ]
    }
  }
}

AgentKit Browser Automation MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is AgentKit Browser Automation?

AgentKit Browser Automation is a browser agent built with Inngest-AgentKit and Firebase-Genkit, featuring an agent system for intelligent web navigation and task execution. It integrates with Playwright MCP to control a browser via an MCP server.

How to use AgentKit Browser Automation?

Install Node.js v20+, clone the repository, install dependencies, and set environment variables for OpenAI and/or Google AI keys. Start the Playwright MCP server on port 8931, then run either npx tsx genkit.ts (for Genkit SDK) or npx tsx agentkit.ts (for Inngest-AgentKit). Optional dev servers provide built‑in observability.

Key features of AgentKit Browser Automation

  • Built on Inngest-AgentKit and Firebase-Genkit
  • Supports GPT (OpenAI) and Gemini (Google) models
  • Uses Playwright MCP for browser control
  • Optional dev server with OpenTelemetry observability
  • Dual execution mode: Genkit SDK or Inngest CLI

Use cases of AgentKit Browser Automation

  • Automate repetitive web browsing tasks
  • Perform intelligent web navigation and data extraction
  • Test web applications with scripted agent behavior
  • Orchestrate multi‑step browser workflows via AI agents

Frequently asked questions

1

What are the prerequisites?

Node.js v20+, npm/yarn, an OpenAI API key (for GPT models), and a Google AI key (for Gemini models).

2

How do I start the Playwright MCP server?

Run `npx @playwright/mcp@latest --port 8931` in a separate terminal window before launching the agent.

3

What is the difference between the Genkit and AgentKit modes?

The Genkit mode (`npx tsx genkit.ts`) uses the Genkit SDK, while the AgentKit mode (`npx tsx agentkit.ts`) uses Inngest-AgentKit. Both achieve browser automation but differ in their agent framework.

4

Can I run a dev server for observability?

Yes. For Genkit mode, run `npx genkit start -- npx tsx --watch genkit.ts`. For AgentKit mode, run `npx inngest-cli@latest dev --no-discovery -u http://localhost:3000/api/inngest -v`. Both provide built‑in OpenTelemetry observability.

Comments

More Browser Automation MCP servers