Vouched has formally donated its Model Context Protocol – Identity (MCP-I) framework to the Decentralized Identity Foundation (DIF), establishing an open standard for how AI agents verify identity, authority, and trust across digital ecosystems. Built on top of Anthropic's existing Model Context Protocol, MCP-I adds a complete identity and delegation layer - using Decentralized Identifiers (DIDs) and Verifiable Credentials (VCs) - so that any service an AI agent approaches can cryptographically verify who authorized it and exactly what it's permitted to do.

Vouched describes it simply: think of it like a power of attorney. The delegation credential is the notarized document, the agent is the attorney, and any service can verify the chain of authority on the spot.

Rosalyn Curato, Chief Innovation Officer and GM of Agentic Security at Vouched, explains the urgency:

"It is time to recontextualize authentication systems designed for humans to one where AI agents increasingly operate autonomously. At Vouched, our ambition is to create a system that supports productive orchestration of AI while eliminating the threat of bad actors."

Rather than building a proprietary solution, Vouched chose to contribute MCP-I as a community starting point -joining DIF's Trusted AI Agents Working Group for open, collaborative development. DIF Executive Director Grace Rachmany noted that at a time when many companies are moving toward closed systems, Vouched's commitment to open standards is exactly what the industry needs.

Originally published on the Biometric Update. For full article, visit the source.