Labsco
srbhptl39 logo

MCP SuperAssistant Chrome Extension

★ 2,500

from srbhptl39

A Chrome extension that integrates MCP tools with AI platforms like ChatGPT and Gemini, allowing users to execute tools and insert results directly into conversations.

🔥🔥🔥🔥✓ VerifiedFreeQuick setup
#automation#social-media#git#search#maps#monitoring

MCP SuperAssistant Chrome Extension

Brings MCP to ChatGPT, Perplexity, Grok, Gemini, Google AI Studio, OpenRouter, Kimi, Github Copilot, Mistral and more...

🌐 Visit Official Website

Overview

MCP SuperAssistant is a Chrome extension that integrates the Model Context Protocol (MCP) tools with AI platforms like Perplexity, ChatGPT, Google Gemini, Google AI Studio, Grokand more. It allows users to execute MCP tools directly from these platforms enhancing the capabilities of web-based AI assistants.

Currently Supported Platforms

Demo Video

Kimi.com

ChatGPT

Watch the demo to see MCP SuperAssistant in action!

MCP SuperAssistant Demo Playlist

What is MCP?

The Model Context Protocol (MCP) is an open standard developed by Anthropic that connects AI assistants to systems where data actually lives, including content repositories, business tools, and development environments. It serves as a universal protocol that enables AI systems to securely and dynamically interact with data sources in real time.

Key Features

  • Multiple AI Platform Support: Works with ChatGPT, Perplexity, Google Gemini, Grok, Google AI Studio, OpenRouter Chat, DeepSeek, Kagi, T3 Chat, GitHub Copilot, Mistral AI, Kimi, Qwen Chat, Z Chat and more

  • Tool Detection: Automatically detects MCP tool calls in AI responses

  • Tool Execution: Execute MCP tools with a single click

  • Tool Result Integration: Seamlessly insert tool execution results back into the AI conversation

  • Render Mode: Renders Function call and Function results.

  • Auto-Execute Mode: Automatically execute detected tools

  • Auto-Submit Mode: Automatically submit chat input after result insertion

  • Push Content Mode: Option to push page content instead of overlaying

  • Preferences Persistence: Remembers sidebar position, size, and settings

  • Dark/Light Mode Support: Adapts to the AI platform's theme

Copy & paste — that's it
flowchart TD
 A[AI Chat Interface] -->|Generate| B[Tool Calls]
 B -->|Detect| C[Extension Detects Tool Calls]
 C -->|Send via SSE| D[MCP Local Proxy Server]
 D -->|Forward| E[Actual MCP Server]
 E -->|Return Results| D
 D -->|Return Results| C
 C -->|Insert| F[Add Results Back to Chat]

Connecting to Local Proxy Server

To connect the Chrome extension to a local server for proxying connections:

Run MCP SuperAssistant Proxy via npx:

Create a config.json file with your MCP server details. For example, to use the Desktop Commander:

Example config.json:

Copy & paste — that's it
{
 "mcpServers": {
 "desktop-commander": {
 "command": "npx",
 "args": [
 "-y",
 "@wonderwhy-er/desktop-commander"
 ]
 }
 }
}

config.json also support other MCP server configurations like remote MCP server URLs. Try composio mcp, zappier mcp, or smithery or any other remote MCP server.

Or use existing config file location from Cursor or other tools:

Copy & paste — that's it
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Start the MCP SuperAssistant Proxy server using one of the following commands:

Copy & paste — that's it
npx -y @srbhptl39/mcp-superassistant-proxy@latest --config ./config.json --outputTransport sse

or

Copy & paste — that's it
npx -y @srbhptl39/mcp-superassistant-proxy --config ./config.json --outputTransport streamableHttp

or

Copy & paste — that's it
npx -y @srbhptl39/mcp-superassistant-proxy --config ./config.json --outputTransport ws

View all available options:

Copy & paste — that's it
npx -y @srbhptl39/mcp-superassistant-proxy@latest --help

This is useful for:

  • Proxying remote MCP servers

  • Adding CORS support to remote servers

  • Providing health endpoints for monitoring

Connection Steps:

  • Start the proxy server using one of the commands above

  • Open the MCP SuperAssistant sidebar in one of the supported AI platforms, this should show the sidebar UI

  • Click on the server status indicator (usually showing as "Disconnected")

  • Enter the local server URL (default: http://localhost:3006/sse) URL format depends on the --outputTransport method used:

  • For SSE: http://localhost:3006/sse

  • For Streamable HTTP: http://localhost:3006/mcp

  • For WebSocket: ws://localhost:3006/message

  • Choose the appropriate transport method (SSE or Streamable HTTP or WebSocket)

  • You can add any remote MCP server URL here as well, if it supports CORS or is proxied via this local proxy server. Try Composio mcp, Zappier mcp, or smithery or any other remote MCP server.

  • Click "Connect" to establish the connection

  • The status indicator should change to "Connected" if successful

Tips & Tricks

  • Turn off search mode (chatgpt, perplexity) in AI chat interfaces for better tool call prompt experience and to prevent MCP SuperAssistant from getting derail.

  • Turn on Reasoning mode (chatgpt, perplexity, grok) in AI chat interfaces, which will help the AI to understand the context better and generate the correct tool calls.

  • Use newer high-end models as they are better at understanding the context and generating the correct tool calls.

  • Copy the MCP instructions prompt and paste it in the AI chat system prompt (Google AI Studio).

  • Mention the specific tools you want to use in your conversation.

  • Use the MCP Auto toggles to control the tool execution.

Development

Prerequisites

  • Node.js (v16+)
  • pnpm

Setup

Copy & paste — that's it
# Install dependencies
pnpm install

# Start development server
pnpm dev

# Build for production
pnpm build

# Create zip package for distribution
pnpm zip

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

  • Fork the repository

  • Create your feature branch (git checkout -b feature/amazing-feature)

  • Commit your changes (git commit -m 'Add some amazing feature')

  • Push to the branch (git push origin feature/amazing-feature)

  • Open a Pull Request

Author

Saurabh Patel

Sponsor & Support

This project is developed entirely in my spare time, driven by a passion for AI and the Model Context Protocol (MCP). As a full-time professional, balancing work commitments with open-source development makes it challenging to contribute regularly and maintain the pace of updates.

Your support helps me dedicate more time to:

  • 🐛 Fixing bugs and addressing issues

  • ✨ Adding new features and platform support

  • 📚 Improving documentation and tutorials

  • 🔄 Keeping dependencies up-to-date

  • 💬 Responding to community requests

Support this project:

  • ⭐ Star the repository to show your appreciation

  • 💖 Sponsor on GitHub to help sustain development

  • 🐦 Follow me on Twitter (@srbhptl39) for updates

  • 📧 For private support or custom implementations, reach out via Twitter

Every contribution, big or small, helps keep this project alive and thriving! 🙏

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

Star History