MCP server · Privacy
Lucairn privacy gateway MCP server
by Declade
Lets your AI clean personal data out of your prompts before they reach the model, and hand you a signed proof of what was removed.
Lucairn is a privacy gateway that sits between your AI assistant and the model it talks to. Before your message goes anywhere, Lucairn finds personal details in it and swaps them for labels like [PERSON_1] or [EMAIL_2]. It is handy for anyone who wants to use ChatGPT or Claude at work but worries about names, emails, or bank details leaving the building.
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 that gives your AI a new skill or a connection to another service. This one connects your AI to Lucairn, a privacy service that cleans personal data out of your prompts. Once it is connected, you just type your request as usual and the helper quietly does the cleaning and proof-keeping behind the scenes.
What this MCP server does
You type a question or task in your AI chat like you always do. The AI passes your message to this helper, which sends it to Lucairn instead of straight to the model. Lucairn scans the text for personal details, replaces them with plain labels, and forwards the cleaned version to the model you picked. The model's answer comes back to you, along with a signed certificate that records what was removed and when.
Click to zoomWhat you can do with it
- Send a prompt through Lucairn so personal details are removed before the model sees them
- Pick which model answers by naming it, such as a Claude or GPT model
- Get a signed certificate for each request showing what was redacted
- Use your own Anthropic or OpenAI account so that provider bills you directly
- Check a certificate later on the Lucairn website to confirm it is genuine
- Test the redaction on the free tier, where labels stay visible in the reply
Try asking your AI
- “Summarize this customer complaint email but strip out the personal details first”
- “Rewrite this contract clause through Lucairn and show me the certificate afterwards”
- “Ask Claude to draft a reply to this message, with names and emails removed”
- “Draft a follow-up note for this client file and give me proof of what was redacted”
What it gives back to you
You get the model's normal answer in the chat, just based on cleaned text. Alongside it you get a certificate, which is a short signed record of what was removed, when, and by which layer of the sanitizer. On the free tier you will see labels like [PERSON_1] left in the reply, which is useful for checking the cleaning worked. On paid tiers the original details are put back before the answer reaches you.
Before you start
What you need
- A Lucairn account and API key (free Developer tier gives 500 requests a month, no card needed)
- Node.js installed on your computer so the npx command can run
- Optionally, your own Anthropic or OpenAI API key if you want that provider to bill you directly
Good to know
Your prompts pass through Lucairn's servers on the way to the model, so if you need everything to stay inside your own building you should look at the self-host option instead.
Install it with your AI
Add Lucairn privacy gateway 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 Lucairn privacy gateway 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 4,066 MCP servers here for you.
Who it's for
Anyone in an office who handles customer, patient, or employee data and wants to use AI without leaking personal details, especially in legal, HR, finance, and support roles.
