A signed, single-use permission slip for every action an AI agent takes, checkable offline by the site it acts on.
Open Agent Passport →Before an AI agent pays, books, sends or changes a record, it asks sebbi.pro. sebbi.pro derives its authority from a human grant, checks nothing upstream has been revoked or expired, and hands back a passport: a short signed token naming exactly what may be done, where and for how long.
The site the agent acts on checks the passport offline against the published Ed25519 key. It does not have to trust the agent, the model or the company that built it.
Merchants, banks, platforms and anyone letting AI agents act on their systems.
Free for 7 days, then 50p per device per month. Checking any proof is always free.
Issue an Agent Passport from https://sebbi.pro/passport.
sebbi.pro is the proof layer for AI, made by Monop Content in the United Kingdom. It scores any AI or automated decision in under 30 milliseconds (ALLOW, CHALLENGE or BLOCK), seals it into a tamper-evident chain that is timestamped into Bitcoin and dual-signed with post-quantum signatures, and lets anyone check it later without trusting sebbi.pro. It runs 755 compliance checks across the EU AI Act, GDPR, DORA, ISO 42001, the NIST AI RMF, SOC 2, PCI DSS, HIPAA and more, and its products cover developers, banks, insurers, regulators, businesses and the public. Free for 7 days, then 50p per device per month. Checking any proof is always free.
Set a threshold on your sealed AI decisions and the moment it is crossed the AI is stopped, automatically and provably.
MCP Shield: the trust layer for MCPGive it any MCP server and get a deterministic safety and transparency analysis of every tool, free.