cyberagents-exchange

mcp
Security Audit
Warn
Health Warn
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Pass
  • Code scan — Scanned 4 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Community-contributed agents, skills, MCP servers, and playbooks for the CyberAgents Exchange

README.md

CyberAgents Exchange

The open exchange for cybersecurity AI agents.
Open-source. Vendor-neutral. Built for security teams.

Website Validate Content Contributors Stars PRs welcome

X YouTube


This repository is the content source for the CyberAgents Exchange — a community directory of open-source AI agents, skills, MCP servers, and playbooks for cybersecurity.

Mission

Security teams 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 directory, not a code host. Listing metadata lives here — the actual agent code lives in contributors' own GitHub repositories. You always get code directly from the author.

The exchange indexes four types of content:

Type What it is Directory
Agents AI agents and tools that automate security tasks agents/
Skills Reusable agent skills that extend AI coding assistants with security capabilities skills/
MCP Servers Model Context Protocol servers for agent connectivity mcp-servers/
Playbooks Multi-agent workflows that chain agents together into end-to-end security processes playbooks/

Browse everything at exchange.tenable.com/browse.

How It Works

Each listing is a single markdown file: YAML frontmatter holding the metadata, and a markdown body describing the project. Contributors submit listings via pull request. Agents are vendor-neutral and run anywhere — not locked to a single platform or license.

When a PR opens, validator.py runs automatically to check required fields, controlled vocabularies, and file placement. Two maintainers then review against the contributing checklist. Merged listings are published to the website on the next build.

Contributing

Read CONTRIBUTING.md before you submit. It covers repository requirements, the Contribution Agreement, frontmatter reference for every listing type, and what reviewers check.

Anyone can contribute. The fastest path is the CyberAgents Exchange Submission Builder skill for Claude Code — install it, run /cyberagents-exchange-submit from your project directory, and it validates your repo, gathers metadata, generates the listing, and opens the PR. It takes about five minutes.

Prefer to do it by hand? Start from a template in templates/ and follow the manual submission steps.

Before you start, your project needs:

  • A public GitHub repository owned by a personal account (not an EMU account)
  • An open-source license — MIT recommended, Apache 2.0 also welcome
  • No secrets anywhere in the git history
  • A README covering purpose, prerequisites, how to run it, outputs, and known limitations

See the Contribute page for a walkthrough.

Repository Layout

agents/          One markdown file per agent listing
skills/          One markdown file per skill listing
mcp-servers/     One markdown file per MCP server listing
playbooks/       One markdown file per playbook listing
templates/       Starter templates for each listing type
docs/            Contribution Agreement, reviewer checklist
validator.py     Schema + controlled-vocabulary validation

validator.py is the source of truth for allowed field values. To propose a new integration, platform, or client, add it in alphabetical order to the relevant Literal[...] list and include the change in your listing PR — see Adding to the Controlled Vocabulary.

Running the validator locally

uv sync
uv run ./validator.py

Optionally install the pre-commit hooks so validation runs on every commit:

uv run pre-commit install

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.

What's the difference between an agent, a skill, an MCP server, and a playbook?
In short: agents run tasks, skills extend coding assistants, MCP servers expose data to agents, and playbooks chain agents into multi-step workflows. Full definitions are in CONTRIBUTING.md.

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.

More at exchange.tenable.com/about.

Questions & Support

Follow along on X and YouTube.

Listings are licensed by their respective authors — check each linked repository for its license. See SECURITY.md and the CyberAgents Contribution Agreement.

Reviews (0)

No results found