AGNTCY: The Next Big AI Platform Enhancing Security in Agentic AI

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. That’s all on the communication and discovery side of the house. Perhaps more importantly, AGNTCY brings security tools to bear in 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 said, explaining the problem agentic AI poses for security.

Among other things, AGNTCY provides cryptographically verifiable identities so that enterprises can ensure their agents are communicating with reputable outside agents. Then there are access controls to ensure the AI agents can only tap into the resources they need, when they need them. If you read our recent piece on the role of access controls in mitigating enterprise security risks, you know this is important. As Pandey explained, to keep AI agents in line, enterprises need to be able to grant and retract access authority at a task level. That’s already non-trivial to do but Pandey noted that even defining what constitutes a task can be hard.

“Those are two simple things that you take for granted that become complicated in an agentic environment,” Pandey said. “So, building out an identity framework and a service that, for example, deals with TBAC – task based access control – is something that we are doing through AGNTCY.”

Then there’s observability and evaluation. AGNTCY is building tools that can help track whether agents are doing what they’re supposed to do and assign a reputation score for their performance.

What’s Next

Going forward, AGNTCY’s direction will be determined by a steering committee comprised of individuals from the project’s formative member companies. But Pandey said he 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.

Indeed, Oracle’s SVP of AI and ML Roger Barga said in a press release accompanying the Linux Foundation announcement 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 step up to the plate to help push AGNTCY forward. You can learn more about the project at agntcy.org.

Frequently Asked Questions (FAQ)

What is AGNTCY?

AGNTCY is an open-source platform developed to provide the necessary infrastructure for AI agents, including discovery, communication, identity verification, and observability. It aims to enhance security in agentic AI deployments.

What problem does AGNTCY solve?

AGNTCY addresses key security gaps in current inter-agent communication protocols, such as the lack of robust authentication and security features in protocols like the Model Context Protocol (MCP). It provides cryptographically verifiable identities and access controls for AI agents.

Is AGNTCY a replacement for MCP or A2A?

No, AGNTCY is interoperable with and not a replacement for protocols like MCP and A2A. It complements these protocols by adding critical security and identity management layers.

Who is developing AGNTCY?

AGNTCY was originally developed by Cisco and is now an open-source project under the Linux Foundation. Formative members include Dell Technologies, Google Cloud, Oracle, and Red Hat.

What are the key security features provided by AGNTCY?

AGNTCY offers cryptographically verifiable identities for AI agents, allowing enterprises to ensure they are communicating with reputable entities. It also implements task-based access control (TBAC) to manage agent permissions and provides observability tools to track agent performance and assign reputation scores.

Why is identity verification important for AI agents?

Identity verification is crucial for enterprises to ensure that their AI agents are interacting with trusted and authorized external agents, thereby mitigating security risks in complex agentic AI systems.

What is Task-Based Access Control (TBAC)?

TBAC is a system implemented by AGNTCY to manage AI agent permissions at a granular, task-specific level. This ensures that agents only access the resources they need, when they need them, enhancing security and control.

What is the future direction of AGNTCY?

The project's direction will be guided by a steering committee, with a strong expected focus on enhancing security, identity management, and trust within multi-agentic AI applications to foster enterprise adoption.

Crypto Market AI's Take

The development and open-sourcing of AGNTCY by Cisco and its adoption by major tech players like Google Cloud, Oracle, and Red Hat, under the Linux Foundation, signify a critical step towards building more secure and trustworthy AI ecosystems. As AI agents become increasingly integrated into enterprise workflows, robust security protocols are paramount. AGNTCY's focus on identity verification and access control directly addresses the inherent security challenges posed by machine-speed, large-scale autonomous operations. This aligns with our own focus on secure and intelligent AI agents that can operate reliably in complex environments. The emphasis on observability and reputation scoring is also key for building confidence in these systems, mirroring the need for transparency and accountability in the cryptocurrency market.

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