AGNTCY: The Next-Gen Secure AI Agent Platform You Need to Know

If you’re working in the AI space, you’ve probably already heard of the Model Context Protocol (MCP). You’re also likely familiar with Google’s Agent to Agent (A2A) protocol. But there’s one more tool that should be on your radar: AGNTCY. Originally developed by Cisco, AGNTCY is a platform designed to provide the infrastructure AI agents need for discovery, communication, identity verification, and observability. In doing so, it fills in key security gaps in current inter-agent communication protocols like MCP. That, in turn, can help give enterprises the confidence they need to press ahead with more complex agentic AI deployments. The project was recently open-sourced and now sits under the Linux Foundation’s collaborative umbrella. In addition to Cisco, Dell Technologies, Google Cloud, Oracle, and Red Hat are working on AGNTCY as formative members of the project group.

How AGNTCY Works

It’s worth noting that AGNTCY isn’t a replacement for MCP or A2A. Vijoy Pandey, SVP of Outshift at Cisco, told Fierce Network that AGNTCY is actually interoperable with both protocols as well as the Secure Low Latency Interactive Messaging (SLIM) protocol. This interoperability covers the communications and discovery aspects. More importantly, AGNTCY brings security tools to the agent-to-agent space. As Fierce noted previously, one of the key issues with MCP is that it lacks robust authentication and security features.

“Agents have human-like attributes but they operate at machine speed and scale. Everything that you’ve built so far has been built either for humans or machines,” Pandey explained, highlighting the security challenges posed by agentic AI.

Among other features, AGNTCY provides cryptographically verifiable identities so enterprises can ensure their agents are communicating with reputable outside agents. It also enforces access controls so AI agents can only tap into the resources they need, when they need them. As Pandey elaborated, enterprises need the ability to grant and retract access authority at a task level to keep AI agents in line. Defining what constitutes a task can be complex, but AGNTCY is working on an identity framework and services that handle task-based access control (TBAC). Additionally, AGNTCY is developing observability and evaluation tools to track whether agents are performing as expected and to assign reputation scores based on their behavior.

What’s Next for AGNTCY

The future direction of AGNTCY will be guided by a steering committee composed of representatives from its formative member companies. Pandey expects a strong focus on security, identity, and trust.

“You’ll see a lot of focus going in that direction as the one burning thing that as a community we need to solve… for enterprises to embrace multi-agentic and agentic applications,” he said.

Oracle’s SVP of AI and ML, Roger Barga, emphasized in a press release that “Enterprise customers need agent infrastructure they can trust for mission-critical workloads.” Pandey concluded with a call to action, urging interested contributors, users, and developers to get involved and help push AGNTCY forward. To learn more, visit agntcy.org.

Frequently Asked Questions (FAQ)

AGNTCY Functionality and Purpose

Q: What is AGNTCY? A: AGNTCY is a platform designed to provide the necessary infrastructure for AI agents to discover, communicate, verify identities, and be observed. It was originally developed by Cisco and is now under the Linux Foundation. Q: How does AGNTCY differ from MCP and A2A protocols? A: AGNTCY is not a replacement for MCP or A2A; instead, it is interoperable with them. Its primary function is to enhance security by filling gaps present in protocols like MCP, offering features such as cryptographically verifiable identities and access controls. Q: What are the key security benefits of using AGNTCY? A: AGNTCY addresses security gaps in inter-agent communication by providing cryptographically verifiable identities for agents, enforcing access controls to limit resource access, and developing tools for observability and reputation scoring based on agent behavior. Q: What is the role of Cisco in the AGNTCY project? A: Cisco originally developed AGNTCY and remains a formative member of the project group, contributing to its development and direction. Q: Who are the other formative members of the AGNTCY project? A: Other formative members include Dell Technologies, Google Cloud, Oracle, and Red Hat.

AGNTCY Development and Future

Q: Why was AGNTCY open-sourced? A: AGNTCY was recently open-sourced and now operates under the Linux Foundation's collaborative umbrella to foster broader community involvement and standardization in multi-agent system infrastructure. Q: What is the expected future focus for AGNTCY? A: The steering committee expects a strong emphasis on security, identity, and trust to enable enterprises to confidently adopt complex agentic AI deployments. Q: How can developers and interested parties get involved with AGNTCY? A: The project encourages interested contributors, users, and developers to get involved and help advance AGNTCY. More information can be found at agntcy.org.

Crypto Market AI's Take

The development and open-sourcing of AGNTCY by prominent tech players like Cisco, Dell, Google Cloud, Oracle, and Red Hat highlight a critical trend in the AI landscape: the increasing need for robust security and interoperability in multi-agent systems. This focus on secure communication and verifiable identity for AI agents is crucial as more sophisticated AI applications are deployed across enterprises. At Crypto Market AI, we are also deeply invested in the intersection of AI and finance, particularly in developing advanced AI agents for trading that can navigate complex market dynamics securely and efficiently. The principles behind AGNTCY, such as verifiable identity and access control, are directly relevant to building trust and transparency in AI-driven financial services. This initiative aligns with our own efforts to foster a secure and intelligent ecosystem for digital asset management and trading.

AGNTCY is the next big AI platform you’ve never heard of