The open exchange for cybersecurity AI agents
Open-source. Vendor-neutral. Built for security teams.
Mission
CISOs are experimenting with AI agents. These innovations are happening in silos. CyberAgents Exchange breaks those silos — a community-driven directory where security professionals discover, share, and chain open-source AI agents.
What It Is
CyberAgents Exchange is a community directory of open-source AI agents, skills, MCP servers, and playbooks for cybersecurity. Listing metadata lives here — actual agent code lives in contributors' GitHub repositories. The exchange indexes four types of content:
Agents
AI agents and tools that automate security tasks.
Skills
Reusable agent skills that extend AI coding assistants with security capabilities.
MCP Servers
Model Context Protocol servers for agent connectivity.
Playbooks
Multi-agent workflows that chain agents together into end-to-end security processes.
How It Works
Contributors submit listings via pull request. Code stays in their repositories — the exchange stores only metadata. Agents are vendor-neutral and run anywhere: not locked to a single platform or license.
Trust & Transparency
All submissions are community-contributed. Code stays in contributors' repositories — the exchange stores only metadata. Review and vet agents before deploying in production.
FAQ
Is this a marketplace? Do agents cost money?
No. The exchange is free and open-source. There are no fees to list or use agents. All code is hosted on contributors' public GitHub repositories.
Is this only for Tenable products?
No. The exchange is vendor-neutral. Agents can integrate with any security product — Tenable, CrowdStrike, SentinelOne, or anything else. Best on Tenable One, but built for all.
Where does the actual code live?
In the contributor's GitHub repository. The exchange is a directory — it stores metadata (name, description, integrations) and links to the source. You always get code directly from the author.
What's the difference between an agent, a skill, an MCP server, and a playbook?
An agent is a standalone AI tool that performs a security task. A skill is a reusable capability that extends AI coding assistants (like Claude Code, Cursor, or Copilot) with security-specific workflows. An MCP server exposes data or capabilities to agents via the Model Context Protocol. A playbook chains multiple agents together into a multi-step workflow for end-to-end security automation.
Who can contribute?
Anyone. Submit a pull request with your listing metadata. See the Contribute page for templates and instructions.
Who's behind this?
CyberAgents Exchange is built and maintained by Tenable's Agentic AI Accelerator practice. Tenable provides the platform, review infrastructure, and flagship agents — the community provides the ecosystem.