Using Trae is like having a team of little AI agents on your desktop, ready to help. But what if you could give those agents a superpower: perfect memory of your specific information?
Refer to our Trae + CustomGPT.ai’s Hosted MCP server docs for more info.
By connecting Trae to your CustomGPT.ai knowledge base, your agents go from general helpers to specialized experts trained on your data.
What’s this MCP thing again?
MCP (Model Context Protocol) is like a universal adapter. It lets your AI agents in Trae plug directly into a data source, like your project on CustomGPT.ai. It’s the bridge that lets your agents access your private knowledge securely.
Why use CustomGPT.ai for your agent’s brain?
- Super accurate: Our system is independently benchmarked as #1 for finding correct answers in documents. Your agents will be more reliable.
- Zero hassle: We manage the servers, security, and all the techy stuff. You just build your agents.
- No extra cost: This is part of your existing CustomGPT.ai plan.
Get the full technical rundown on our Hosted MCP launch blog post.
How Your Agent Gets its Information
Trae uses the same kind of helper as Claude to connect to your data
You, chatting with an agent in Trae
│
▼
┌─────────────────────────────────┐
│ Your PC runs a little helper │
│ (called `supergateway`) │
└─────────────────────────────────┘
│ (Sends question securely)
▼
┌─────────────────────────────────┐
│ CustomGPT.ai Server │
│ (Searches your private files) │
└─────────────────────────────────┘
│ (Sends answer back)
▼
┌─────────────────────────────────┐
│ Your PC's helper gets the │
│ answer │
└─────────────────────────────────┘
│
▼
Your Trae agent gives you the smart answer!What you’ll need first:
- A CustomGPT.ai account (the free trial is fine).
- A project on CustomGPT.ai with your files uploaded.
- The Trae application.
- Node.js (version 18 or newer) installed on your computer.
Let’s Hook It Up: Step-by-Step
- Get your secret token: Log in to CustomGPT.ai, open your project, and head to Deploy ➞ MCP Server (Beta). Hit Generate MCP Token.
- Open Trae’s agent settings: In the Trae app, press Ctrl+U to open the Agents panel.
- Go to manual config: Click the gear icon (AI Management) ➜ MCP ➜ Configure Manually.
- Paste the code: Paste this block into the window. Just remember to put your own <PROJECT_ID> and <TOKEN> in there.
{
"mcpServers": {
"customgpt-mcp-server": {
"command": "npx",
"args": [
"-y",
"supergateway",
"--sse",
"https://mcp.customgpt.ai/projects/<PROJECT_ID>/sse",
"--header",
"Authorization: Bearer <TOKEN>"
]
}
}
}- Confirm and restart: Click Confirm and then restart the Trae app.
Now you can pick your new customgpt-mcp-server from the Agents list and start chatting. Your agent is now an expert on your stuff!
Watch it in action:
Your Turn to Build!
So there you have it. No more generic answers! Your favorite AI tool is now your personal expert, with a direct line to the documents and data you care about most. It’s a true game-changer for getting things done.
Why not give it a try? Head over to CustomGPT.ai to start a free trial and create your own private AI brain.
We can’t wait to see what you build with it!
P.S If are into MCP world, you will definitely live this MCP AMA that we did with Pinecone folks and other MCP folks (Santiago).
Find it here:
Further Reading
For those interested in exploring MCP in greater depth, check out the following resources:
- What Is Model Context Protocol (MCP)?
A comprehensive introduction to MCP’s origins, goals, and why it’s becoming the de facto “USB-C” for AI integrations. - Top 124 MCP Servers, MCP Clients & Tools (2025 Guide)
A curated catalog of production-ready MCP servers and clients—both open-source and proprietary—showcasing plug-and-play tools you can use today. - Problems MCP Model Context Protocol Solves
An exploration of the real-world pain points (API sprawl, ad-hoc integrations, security gaps) that MCP was designed to eliminate. - The Model Context Protocol (MCP) Architecture (2025)
A deep dive into MCP’s component layers, sequence diagrams, security considerations, and production-grade deployment patterns.
Priyansh is Developer Relations Advocate who loves technology, writer about them, creates deeply researched content about them.
