OpenDia

Provides browser automation via MCP using local browser data and sessions for AI-assisted workflows.

javascript

1.7k

GitHub Stars

javascript

Language

4 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "aaronjmars-opendia": {
      "command": "npx",
      "args": [
        "opendia"
      ]
    }
  }
}

OpenDia MCP Server lets AI models control your browser locally, using your existing sessions, data, and extensions. It enables seamless automation across sites while keeping everything private and running on your machine, so you can build powerful browser-assisted workflows without leaving your environment.

How to use

You interact with the OpenDia MCP Server by connecting an AI client that supports MCP, such as Claude Desktop or Cursor, to the local server you run on your machine. The server exposes browser automation capabilities that let the AI analyze pages, click elements, fill forms, manage tabs, and access your bookmarks and history. Start by running the server, then connect your MCP client using the provided configuration, and finally issue prompts that describe the browser tasks you want to perform.

How to install

Prerequisites: you need Node.js and npm installed on your machine. Ensure you have a compatible MCP client (e.g., Claude Desktop) ready to connect to the local server.

Install the server via the standard start command used in setup.
Load or configure the MCP connection so your client can reach the local OpenDia server on the default ports.
Start the server and verify the connection from your MCP client. When connected, the client will auto-discover the local WebSocket endpoint and begin interacting with your browser.

Configuration & usage modes

Local Mode (default) runs the server locally and connects to the browser extension. The typical flow uses the following setup: the browser extension runs in your browser and communicates with the local server to perform actions on web pages.

Port configuration lets you customize ports for WebSocket and HTTP endpoints. You can run with specific ports to avoid conflicts, for example by setting --port for WebSocket and --http-port for HTTP.

Auto-Tunnel mode can expose your local server through ngrok for remote access. This maintains local processing while giving online AI services a reachable URL. ngrok must be installed and configured with an authtoken.

Security & privacy

All processing for OpenDia stays on your machine. Your data—browsing activity, history, passwords, and session data—remains private and under your control. The solution runs locally, and you decide when to enable the extension and connect to the server.

The server requires broad browser permissions to function, so use it only with trusted AI models and in environments where browser automation is appropriate.

Troubleshooting & notes

If you encounter connection issues, verify that the MCP client is configured to connect to the local host and that the browser extension is loaded and enabled. Check that the WebSocket endpoint is reachable and that the extension can communicate with the local server.

Example prompts to try

Summarize the articles I read today and post a Twitter thread with the key insights.

Available tools

Smart Page Understanding

AI analyzes pages to identify buttons, forms, and interactive elements, enabling precise interaction and automation.

Natural Interactions

AI can click elements, fill forms, navigate pages, and interact with modern web apps while bypassing common automation blocks.

Tab & Window Management

AI manages multiple tabs and windows, coordinating cross-site tasks and workflows.

Access Your Browser Data

AI can access bookmarks, history, and current page content to support research and retrieval tasks.

Anti-Detection Features

Specialized behavior to reduce automation detection on social platforms during posting and interaction.

Page Styling & Customization

AI can apply themes and visual effects to pages to improve readability or presentation.