Didit
All-in-one identity platform for fast human verification.
144 followers
All-in-one identity platform for fast human verification.
144 followers
Didit is an all-in-one identity platform that lets humans prove who they are starting with a face scan. It powers the fastest identity verification in the market, fights fraud by default, and unifies all identity checks with simple pay-per-use pricing.
This is the 4th launch from Didit. View more
Didit MCP
Launching today
Connect ChatGPT, Claude, Cursor, VS Code or Codex to Didit. Ask in plain English: your agent builds KYC and KYB flows, checks IDs against government databases, screens people and wallets for AML and back-tests fraud rules.
Launch Team
Render Sandboxes: a computer for every agentRun untrusted code safely. Idle sandboxes cost nothing
Promoted
Hey Product Hunt 👋
Alberto here, co-founder of Didit with my twin brother Alejandro. 3,000+ companies use Didit for identity verification and fraud prevention.
These are complex products. Setting up a verification flow per country, tuning fraud rules or working a review queue always needed a developer and a lot of time.
So today we're officially launching the Didit MCP server. Connect it to ChatGPT, Claude, Cursor, VS Code or Codex, and anyone on your team, including your compliance officer, can set up and run Didit by asking:
→ "Add government ID checks for Mexico and Brazil, then give me a test link"
→ "Why was this user declined?"
→ "Back-test this fraud rule on the last 90 days"
It only gets your console role's access, in the orgs you pick.
🚀 Try it: docs.didit.me/integration/mcp/overview
What would you ask your agent to do first?
The "why was this user declined?" and back-testing a fraud rule on the last 90 days are the bits that stood out to me — verification is usually a black box, and being able to interrogate it in plain English from Cursor or Claude feels like a real shift. I'm curious how the permissions play out in practice: can you hand it a read-only role for digging into declines, and keep a separate approval step before it actually changes a live rule? That split would make me a lot more comfortable letting an agent near this stuff.
Being able to build KYC and AML workflows through simple prompts could save teams a lot of setup time