Connect your own AI

Ask your own AI about your own record.

Indaga speaks MCP, the open protocol AI assistants use to reach your data. Point Claude, ChatGPT or any other assistant at your record and ask in your own words. The assistant does the talking; Indaga supplies the evidence and its limits.

What your AI can do once it is connected

Connect your AI

€7 a month. Included with the full report.

Your AI (Claude, ChatGPT or another assistant) reads your Indaga record and answers in its own words. The plan unlocks no readings: your report stays the free edition unless you buy the full report.

Choose your AI

Pick the one you use. You set it up once.

Add Indaga to Claude

Add Indaga to Claude
  1. Claude opens in a new tab with Indaga’s name and address filled in. Press Add.
  2. Sign in to Indaga and approve. Claude gets its own credential, which you can revoke here at any time.
  3. Start a new chat and ask “What does Indaga know about my sleep?”

If Claude shows Authentication “None”, switch it to “Always required”: with “None” Claude never asks for a sign-in, and nothing loads.

Set up once, it follows your Claude account: the web, the desktop app and the Claude app on your phone. On a phone, the button opens claude.ai in your browser.

Add Indaga to ChatGPT

Add to ChatGPTCopies Indaga’s address and opens ChatGPT.
https://app.indaga.ai/v1/mcp
  1. In ChatGPT, press + and choose Add custom MCP server.
  2. Name it Indaga, paste the address as the Server URL and choose OAuth.
  3. Tick I understand and want to continue, press Create as a plugin, then Install. Sign in to Indaga and approve.
  4. In a chat, type @ and pick Indaga.

Set it up once at chatgpt.com, in a browser or ChatGPT’s desktop app. It is then a plugin on your ChatGPT account, which the ChatGPT app on your phone uses too. On a work or school account, your admin may need to allow it.

Connect Claude Code

Claude Code signs in to Indaga itself. Run these two lines in a terminal; the second opens Indaga in your browser, where you sign in and approve.

claude mcp add --transport http --scope user indaga https://app.indaga.ai/v1/mcp
claude mcp login indaga

If Claude Code says Indaga’s token was rejected, an old credential is still set. Run claude mcp get indaga to see which entry it uses, remove it with claude mcp remove indaga until none is left, then run the two lines again.

A tool that cannot sign in takes a credential in a header instead. Other desktop tools that accept a Bearer credential can use the one you make here.

Sign in to create one

Sign in to download the skills bundle for these tools.

Other assistants

Other assistants that support MCP with OAuth sign-in can use the same address and the same sign-in. Copy it, paste it where your assistant asks for a server, and choose OAuth when it asks how to authenticate. You sign in to Indaga and approve, exactly as with Claude.

https://app.indaga.ai/v1/mcp

Answering your questions means sending parts of your health record — including genetic and health data — to whichever AI provider you choose. They handle it under their terms, not Indaga’s, and most process data outside the EU. You will see this again on the approval screen, with the provider named, before anything is shared.

Every answer arrives with its evidence and its limits attached, and the AI is told to show them. Your AI is told which of these your record can answer today, and which it cannot yet — it will say so rather than guess.

  • What changed this week?Draws on two weeks of wearable data.
  • Am I recovered enough to train hard today?Draws on HRV and breathing rate.
  • How regular has my sleep been?Draws on seven nights of sleep.
  • When is my biological midnight and best training window?Draws on two weeks of heart rate.
  • How fit am I for my age?Draws on a VO₂max reading and your age.
  • What does my DNA say about lactose, folate, alcohol?Draws on your genome.
  • Show me my genome report.Draws on your genome.
  • What is my cholesterol?Draws on a blood test you uploaded.

Before your first question, your AI asks Indaga for a briefing about your record — and for the rules it has to answer under. Three things, and nothing else.

  • The briefing. What your record holds — how many nights of sleep, which years of heart rate, whether a genome or a blood test is on file — in counts and dates. Never a reading: it says a blood test exists, not what the blood test said.
  • The rules. A value that was never measured is unknown, never normal. A value that is old is quoted with the date it was taken. A percentile, a predictor score or a “Pathogenic” label is not a diagnosis.
  • The boundary. It reads your record, logs what you tell it, can change your supplement and health plans, and can take back what it logged itself — the full list is below. It cannot erase your whole record, export it or change your settings. It can get a link to your printed report, which works for 30 minutes.

A connected AI can

  • Read your record — wearables, labs, sleep, genome and the readings derived from them.
  • Log statements you give it: journal entries, notes, tags, meals, supplements taken, health readings and intake targets.
  • Record lab results you state, or propose blood test results it read from a report, for you to confirm in the Indaga iOS app.
  • Set or end your supplement plan, and edit, clear or reset sections of your health plan. Earlier plan entries remain on the record.
  • Save briefs and start an experiment protocol with its declared outcome.
  • Register or stop its own routines. The AI runs the schedule; Indaga records it.
  • Withdraw records created through this connection, with a reason. It cannot withdraw records created by you or another connection.

It cannot

  • Erase your whole record.
  • Confirm lab proposals for you.
  • Export your record or start background tasks.
  • Change your settings.

It can get a link to your printed report, which works for 30 minutes.

How each of these works, with examples