If you’re using Windsurf, you’re already playing with some powerful AI workflows. But what if you could add your own secret ingredient to the mix? Your company’s internal data, your personal research, anything.
Refer to our Windsurf + CustomGPT.ai’s Hosted MCP server docs for more info.
By connecting your CustomGPT.ai agent to Windsurf, you can ground its powerful abilities in the information that matters most to you.
What’s MCP?
MCP (Model Context Protocol) is just a fancy name for a standard plug. It lets different AI tools and data sources talk to each other without any hassle. For Windsurf, it means you can easily “plug in” a brain like CustomGPT.ai that’s been trained on your private files.
Why is CustomGPT.ai a great choice for this?
- It’s smart: Our system is ranked #1 for accuracy, so you get reliable answers from your files.
- It’s easy: We take care of all the server maintenance and security for you.
- It’s included: There’s no extra charge to use this with your CustomGPT.ai plan.
Want to read the full story? Check out the Hosted MCP launch blog post.
How Your Data Flows in Windsurf
Just like with Cursor, Windsurf connects directly and securely
You, using the "Vision" panel in Windsurf
│
│ (Directly and securely to our server)
▼
┌───────────────────────────────────────────┐
│ CustomGPT.ai Server │
│ (Finds the right info in your files) │
└───────────────────────────────────────────┘
│
│ (Sends the answer right back to Windsurf)
▼
The answer from your data appears in Windsurf!What you’ll need first:
- A CustomGPT.ai account (a free trial works).
- A project in CustomGPT.ai with your data all loaded up.
- The Windsurf application.
Let’s Hook It Up: Step-by-Step
- Grab your config: Log into your CustomGPT.ai account, open your project, and go to Deploy ➞ MCP Server (Beta). Generate a token. Copy the whole JSON block that appears.
- Open Windsurf settings: In Windsurf, go to Settings ➜ Advanced.
- Go to Cascade: In the sidebar on the left, click on Cascade.
- Add a custom server: Click Add Server ➜ Add custom server +.
- Paste the JSON: Paste the entire JSON block you copied from CustomGPT.ai. It will look like this, but with your details filled in.
{
"mcpServers": {
"customgpt-mcp-server": {
"url": "https://mcp.customgpt.ai/projects/<PROJECT_ID>/sse?token=<TOKEN>"
}
}
}- Save it. If the little light next to the server turns green, you’re good to go!
Now you can use the “Vision” panel in Windsurf to query your private data and include it in your AI workflows.
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.
