Platform layer — AI & LLM
AI agent authorization.
MCP gives AI agents data connectivity. It does not give them identity, rights or audit. That layer is what we run. OID4VCI-based credentials, SD-JWT claims, EU Data Act compliant by design.
What MCP gives you — and what it doesn't
MCP is the standard way AI agents connect to data sources and tools. It handles connectivity. It does not handle the question of which agent is making the call, what that agent is allowed to do, or how to prove later what it did. In an EU Data Act world, those questions are not optional. Protium adds the authorization, credential and audit layer above MCP — without breaking MCP.
How it works
Agent gets a verifiable credential
Via OID4VCI, each AI agent receives a verifiable credential that carries its identity and its assigned data rights. SD-JWT allows selective disclosure of those rights per call.
Credential is presented at the MCP boundary
When the agent calls an MCP server, the authorization layer validates the credential, checks the rights, and either allows, scopes or denies the call.
Every action is auditable
Every credential issuance, presentation and authorization decision is logged. This is the audit trail your DPO and your compliance officer need.
Standards used
OID4VCI
OpenID for Verifiable Credential Issuance.
SD-JWT
Privacy-preserving, selectively disclosable credentials.
EUDI Wallet ARF v1.5+
European Digital Identity Wallet reference architecture.
iSHARE v3
Certified trust framework for data spaces.
MCP-compatible
Authorization layer for the Model Context Protocol ecosystem.
EU Data Act
In force since September 2025.
Integration patterns
For enterprises deploying internal AI agents
Wraps your MCP servers and LLM platforms with credential-based authorization. Integrates with your IAM.
For platform teams exposing data to partner agents
Issue credentials to partner AI agents. Govern what they can access. Provide audit trails to partners and regulators.
For data spaces with AI participants
AI agents become first-class participants in the data space — with identity, rights and consent, just like human participants and partner systems.