MCP Superassistant
Brings MCP to ChatGPT, DeepSeek, Perplexity, Grok, Gemini, Google AI Studio, OpenRouter, DeepSeek, T3 Chat and more...
What is MCP Superassistant?
MCP Superassistant is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to brings mcp to chatgpt, deepseek, perplexity, grok, gemini, google ai studio, openrouter, deepseek, t3 chat and more...
Brings MCP to ChatGPT, DeepSeek, Perplexity, Grok, Gemini, Google AI Studio, OpenRouter, DeepSeek, T3 Chat and more...
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Brings MCP to ChatGPT, DeepSeek, Perplexity, Grok, Gemini, G
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-superassistantConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Superassistant
MCP SuperAssistant is a browser extension that injects MCP tool-calling capabilities into AI chat interfaces that do not natively support the Model Context Protocol, including ChatGPT, Google Gemini, Perplexity, Grok, Google AI Studio, OpenRouter, DeepSeek, GitHub Copilot, Mistral AI, and more. It works alongside a local proxy server that connects to your existing MCP servers, detects tool call output in AI responses, and can automatically execute those calls and feed results back into the conversation. This lets users bring any MCP server's tools to whichever AI chat platform they prefer.
Prerequisites
- Chrome or Firefox browser installed
- Node.js 18+ and npx available (for the local proxy server)
- One or more MCP servers already configured and runnable
- An account on a supported AI platform (ChatGPT, Gemini, Perplexity, etc.)
Install the browser extension
Install MCP SuperAssistant from the Chrome Web Store or Firefox Add-ons. Search for 'MCP SuperAssistant' or load an unpacked build from GitHub releases for development.
Create your MCP server config file
Create a config.json listing the MCP servers you want to expose through the proxy.
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"]
}
}
}Start the local proxy server
Launch the SuperAssistant proxy, pointing it at your config file. It exposes your MCP servers over SSE on port 3006 by default.
npx -y @srbhptl39/mcp-superassistant-proxy@latest --config ./config.json --outputTransport sseConnect the extension to the proxy
Open a supported AI platform in your browser. The SuperAssistant sidebar appears automatically. Enter the proxy URL (http://localhost:3006/sse) and click Connect.
Inject MCP instructions into your conversation
Use the extension's sidebar to insert the MCP system prompt into your AI conversation, then specify which tools you want the AI to use.
Execute tool calls
When the AI generates a tool call in its response, the extension detects it and displays a RUN button. Click it (or enable Auto-Execute) to run the tool and feed results back automatically.
MCP Superassistant Examples
Client configuration
Proxy server config.json for MCP SuperAssistant defining which MCP servers to expose.
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/home/user/docs"]
},
"fetch": {
"command": "uvx",
"args": ["mcp-server-fetch"]
}
}
}Prompts to try
Example prompts to use in supported AI platforms once connected via MCP SuperAssistant.
- "Read the file /home/user/docs/report.txt and summarize it"
- "Fetch the content of https://example.com and extract all links"
- "List the files in my documents folder"
- "Search for all markdown files containing the word 'budget'"
- "Write a summary of what you find in my project directory"Troubleshooting MCP Superassistant
Sidebar does not appear on the AI platform
Ensure the extension is enabled in your browser's extension manager. Reload the AI platform tab after enabling. The extension supports 13+ platforms — check the GitHub README for the current supported list.
Extension cannot connect to the proxy at localhost:3006
Verify the proxy server is running by visiting http://localhost:3006/sse in your browser — you should see a streaming response. If the proxy crashed, restart it with the npx command. Firewall rules can block localhost connections from browser extensions on some systems.
Tool calls are detected but execution fails with errors
Check the proxy server terminal output for error messages from the underlying MCP server. Ensure the MCP server referenced in config.json is installed and its dependencies are available on PATH.
Frequently Asked Questions about MCP Superassistant
What is MCP Superassistant?
MCP Superassistant is a Model Context Protocol (MCP) server that brings mcp to chatgpt, deepseek, perplexity, grok, gemini, google ai studio, openrouter, deepseek, t3 chat and more... It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Superassistant?
Follow the installation instructions on the MCP Superassistant GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCP Superassistant?
MCP Superassistant works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Superassistant free to use?
Yes, MCP Superassistant is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
MCP Superassistant Alternatives — Similar Coding Agents Servers
Looking for alternatives to MCP Superassistant? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MCP Superassistant in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MCP Superassistant?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.