MCP server · Privacy

Rohan Protocol MCP server

Adds a privacy shield to your AI's tool calls so secrets and private details stay out of the chat.

Privacy Security For it and development Security

Rohan Protocol is a helper that sits between your AI and the tools it uses, and tries to keep sensitive details out of the conversation. It is made for people who let an AI run tools that touch passwords, keys, or private data. It is a public beta, so treat it as an extra layer, not a guarantee.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program you connect to your AI so it gains a new skill or a link to another service. This one links your AI to the Rohan Protocol shield, which checks the details of a tool call before they reach the model. When you ask your AI to do something, this helper handles the private parts in a separate, temporary memory space instead of putting them in the chat.

What this MCP server does

You ask your AI to run a task that involves private details, like an API key or a password. Your AI passes those details to this helper instead of typing them into the conversation. The helper checks the request for hidden tricks, such as sneaky characters used in prompt injection, and strips them out. It then creates a short digital fingerprint of what was asked and sends that to the Rohan service, which records it on the Midnight network without you paying fees. You get back a confirmation that the request was checked and anchored, while the private details never appear in the chat.

What you can do with it

Check a tool request for hidden prompt injection characters before it runs
Keep secrets like API keys and passwords out of the AI chat window
Create a short digital fingerprint of what your AI intended to do
Record that fingerprint on the Midnight network without paying gas fees
Wipe the private details from temporary memory right after the check
Use it from Claude Desktop, Cursor, or Windsurf

Try asking your AI

“Use the Rohan shield to check this request before you run it: send the report to the finance team with the API key attached”
“Run a Rohan handshake for agent 42 with the intent to update the customer record, and keep the private payload out of our chat”
“Check this tool call for hidden prompt injection characters and tell me if anything was stripped”
“Anchor the intent for this action on Midnight and show me the confirmation”

What it gives back to you

You get a short confirmation in the chat, usually a status message and a 32-byte fingerprint that stands for what your AI intended to do. You may also see a note that the request was checked and anchored on the Midnight network. The private details themselves are not shown back to you in the chat.

Before you start

What you need

Node.js 18 or newer on your computer
The Claude desktop app, Cursor, or Windsurf
Internet access to reach the Rohan relayer service

Good to know

This is a public beta, and the README says the stronger privacy proof is still being researched, so do not treat it as a full guarantee that secrets can never leak.

Install it with your AI

Add Rohan Protocol MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Rohan Protocol MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,609 MCP servers here for you.