OneTool MCP
One server your agent calls as Python code — search, files, databases, diagrams, memory, plus a proxy for the MCP servers you already run.Read full description
beycomLABSCO SUMMARY
It works because the platform never learns about MCP — the extension does the detecting.
Nothing is asked of ChatGPT or Gemini: you paste an instructions prompt so the model knows what to write, and the extension watches the reply for tool calls, runs them and pastes the results back. That is also the limitation — the loop depends on the model formatting its call correctly, which is why the instructions prompt is a required step rather than a nicety.
What it is
A Chrome and Firefox extension that adds a sidebar to web AI platforms and connects it to your MCP servers through a local proxy. The model writes a tool call in its reply, the extension spots it, runs it against your real MCP server, and inserts the result back into the conversation.
What you get
- MCP tools inside ChatGPT, Google Gemini, Perplexity, Grok, Google AI Studio, OpenRouter Chat, DeepSeek, T3 Chat, GitHub Copilot, Mistral AI, Kimi, Qwen Chat and Z Chat
- Tool calls detected automatically in the model's output, executed on click, and their results inserted back into the chat
- Auto-execute and auto-submit modes for running the loop without clicking, and a render mode that formats function calls and results
- Per-tool enable and disable from the sidebar, plus a hover list of available tools and an insert button for the working-instructions prompt the platform needs
- A local proxy that reads a standard
mcpServersconfig — including an existing Claude Desktop config file — and speaks SSE, Streamable HTTP or WebSocket, adding CORS and health endpoints for remote servers
Requirements
The extension from the Chrome Web Store or Firefox Add-ons, plus a local proxy started with npx -y @srbhptl39/mcp-superassistant-proxy@latest --config ./config.json --outputTransport sse, or with streamableHttp or ws instead. The sidebar connects to that proxy — http://localhost:3006/sse for SSE, http://localhost:3006/mcp for Streamable HTTP, ws://localhost:3006/message for WebSocket — or straight to a remote MCP server URL that supports CORS. MIT licensed. Version 0.6.0.
Setup effort
Follow the published steps
USE CASES
01
Using your MCP servers inside ChatGPT or Gemini
Start the proxy against your existing config, open the sidebar on the platform, connect, and insert the instructions prompt — the tools you already run locally become available in that chat.
02
Reusing the server config you already have
Point the proxy at your Claude Desktop config file instead of writing a new one; remote MCP server URLs work in the same file.
03
Keeping a long tool loop moving
Turn on auto-execute and auto-submit so detected calls run and results are submitted without a click at every step.
04
Limiting what a web chat can reach
Enable only the tools that task needs from the sidebar, rather than exposing every server you have configured.
BEFORE YOU INSTALL
What to know first
Requires
- npx on PATH
- Node.js
INSTALLATION
Connect your client
Server setup
Install the MCP SuperAssistant extension from the Chrome Web Store (https://chromewebstore.google.com/detail/mcp-superassistant/kngiafgkdnlkgmefdafaibkibegkcaef) or Firefox Add-ons (https://addons.mozilla.org/en-US/firefox/addon/mcp-superassistant/).
Create a config.json that lists the MCP servers you want the web chat to reach, in the usual mcpServers format — or point --config at a config file you already have, such as Claude Desktop's claude_desktop_config.json.
TERMINAL
npx -y @srbhptl39/mcp-superassistant-proxy@latest --config ./config.json --outputTransport sseOpen the MCP SuperAssistant sidebar on a supported AI platform, click the server status indicator (it shows Disconnected), enter http://localhost:3006/sse and click Connect. With --outputTransport streamableHttp use http://localhost:3006/mcp; with ws use ws://localhost:3006/message.
Insert the instructions prompt from the sidebar into the chat so the model knows how to write tool calls.
