.jpg)
Vouched, a leader in identity verification and agentic identity infrastructure, has donated its Model Context Protocol – Identity (MCP-I) framework to the Decentralized Identity Foundation (DIF). This open-source contribution advances standardized trust and security for AI agents by enabling cryptographically verifiable identity, authority, and delegation in autonomous workflows.
As AI agents take on autonomous roles in digital ecosystems, verifying their identity, authorization, and permitted actions becomes essential to prevent fraud and maintain trust across organizations.
Traditional identity systems, built for human users, fall short in agentic scenarios where AI operates independently. MCP-I recontextualizes authentication by using DIDs and VCs to convey workflow-specific claims—such as who authorized the agent and its exact permissions—securely and without prior party coordination.
“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. We look forward to partnering with the innovators and thinkers, like DIF, leading this transformation,” said Rosalyn Curato, Chief Innovation Officer and GM of Agentic Security at Vouched.
MCP-I builds directly on the open-sourced Model Context Protocol (MCP), originally developed by Anthropic under the Agentic AI Foundation (Linux Foundation), which negotiates data access for external agents. MCP-I adds a robust identity and delegation layer, enabling cryptographically secure verification of both agents and their human principals.
MCP-I offers a progressive path to implementation:
This structure supports organizations of varying maturity while driving toward comprehensive, privacy-preserving standards.
The DIF Trusted AI Agents Working Group will now oversee MCP-I’s development through a dedicated Task Force, fostering open collaboration among developers, standards bodies, and industry partners. Early proofs-of-concept demonstrate MCP-I enabling secure agentic commerce, where verified AI agents complete purchases on behalf of users with clear accountability for merchants.
“Vouched is making a significant contribution to DIF with its MCP-I protocol and participation in our Trusted AI Agents Working group,” said Grace Rachmany, Executive Director at DIF. “At a time when many companies are turning towards proprietary solutions, Vouched has recognized the importance of open source and open standards for the industry. MCP-I is a major step in that direction, and we are excited to collaborate on this effort to deploy Agentic AI safely.”
By contributing MCP-I to DIF, Vouched supports the foundation’s mission to create practical, interoperable standards for secure, privacy-focused digital interactions in an increasingly agent-driven world.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.