AGNTCY: The Next-Generation Secure AI Agent Platform You Haven't Heard Of

By Diana Goovaerts 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 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

AGNTCY isn’t a replacement for MCP or A2A. Vijoy Pandey, SVP of Outshift at Cisco, told Fierce Network that AGNTCY is interoperable with both protocols as well as the Secure Low Latency Interactive Messaging (SLIM) protocol. This interoperability applies to communication and discovery. More importantly, AGNTCY brings enhanced security tools to the agent-to-agent space. One of the key issues with MCP is its lack of 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 unique security challenges posed by agentic AI.

Among other features, AGNTCY provides cryptographically verifiable identities so enterprises can ensure their agents communicate only with reputable outside agents. It also enforces access controls, ensuring AI agents can only access the resources they need, exactly when they need them. This task-based access control (TBAC) is critical for enterprise security. As Pandey noted, granting and retracting access authority at a task level is complex, especially when defining what constitutes a task in an agentic environment.

“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.”

AGNTCY also focuses on observability and evaluation, developing tools to track whether agents perform as expected and assigning reputation scores based on their behavior.

What’s Next for AGNTCY

The future direction of AGNTCY will be guided by a steering committee comprising members from the project’s formative 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 the importance of trust in agent infrastructure for mission-critical workloads in a press release accompanying the Linux Foundation announcement. Pandey concluded with a call to action, urging contributors, users, and developers to get involved and help advance AGNTCY. You can learn more about the project at agntcy.org.

Source: Originally published at Fierce Network on August 5, 2025.

Frequently Asked Questions (FAQ)

AGNTCY Functionality and Purpose

Q: What is AGNTCY? A: AGNTCY is a platform designed to provide the essential infrastructure for AI agents, enabling discovery, secure communication, identity verification, and observability. Q: How does AGNTCY differ from MCP and A2A protocols? A: AGNTCY is not a replacement for MCP or A2A but is interoperable with them. Its primary advantage is the integration of enhanced security features, addressing gaps in protocols like MCP, particularly in authentication and verification. Q: What specific security enhancements does AGNTCY offer? A: AGNTCY provides cryptographically verifiable identities for agents, allowing enterprises to ensure communication only occurs with reputable agents. It also enforces task-based access control (TBAC) to manage agent permissions precisely. Q: How does AGNTCY handle agent behavior and performance? A: AGNTCY focuses on observability and evaluation, developing tools to track agent performance against expectations and assign reputation scores based on their observed behavior.

AGNTCY Development and Community

Q: Who developed AGNTCY and who is involved in its development? A: AGNTCY was originally developed by Cisco. It is now an open-sourced project under the Linux Foundation, with formative members including Dell Technologies, Google Cloud, Oracle, and Red Hat. Q: What is the future direction of AGNTCY? A: The project's future direction will be guided by a steering committee, with a strong emphasis on enhancing security, identity, and trust within AI agent ecosystems, which are crucial for enterprise adoption of agentic AI.

Crypto Market AI's Take

The development of platforms like AGNTCY is a critical step towards the wider adoption of sophisticated AI agents in enterprise environments. By addressing fundamental security and trust issues in agent-to-agent communication, AGNTCY lays the groundwork for more complex and reliable AI deployments. This aligns with our mission at Crypto Market AI to leverage AI for secure and efficient financial solutions. As AI agents become more integrated into various sectors, the need for robust infrastructure that ensures verifiable identities and controlled access, as provided by AGNTCY, will only grow. This focus on security and trust is paramount for building confidence in AI-driven financial systems, from automated trading strategies to personalized financial advice.

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