# Tracecat — Agentic Security Automation

> Tracecat is an open-source security automation platform for teams and AI agents, built on Temporal with sandboxed tool runs and a self-hostable UI.

## Install

Copy the content below into your project:

## Quick Use

```bash
git clone https://github.com/TracecatHQ/tracecat.git
cd tracecat
cp .env.example .env

# production-like local stack
docker compose -f docker-compose.local.yml up

# (optional) dev stack
docker compose -f docker-compose.dev.yml up
```

## Intro

Tracecat is an open-source security automation platform for teams and AI agents, built on Temporal with sandboxed tool runs and a self-hostable UI.

- **Best for:** Security engineering, SOC automation, and agent-driven playbooks
- **Works with:** Docker Compose; Temporal; PostgreSQL; integrates with MCP servers (per README)
- **Setup time:** 30–90 minutes

## Practical Notes

- GitHub: 3,598 stars · 359 forks; pushed 2026-05-12 (verified via GitHub API).
- Repo includes `docker-compose.dev.yml` + `docker-compose.local.yml` and a `justfile` wrapper for common workflows.
- Per README: sandboxed-by-default with `nsjail` and durable workflows on Temporal.

## Main

A practical adoption path:

1. **Start with one playbook.** Pick a repeatable task (phishing triage, IOC enrichment, alert dedupe) and model it as a workflow.
2. **Gate “risky tools.”** Put human approval in front of actions that touch production systems or customer data.
3. **Version your scripts.** Use the code-native registry idea: keep custom Python tools in Git and sync them into Tracecat.
4. **Treat MCP servers as dependencies.** Prefer a small, curated set of MCP servers and pin their configs for reproducibility.

If you run this on developer laptops, keep secrets in env vars and rotate them often; for production, use a dedicated environment and audited credentials.

### FAQ

**Q: Do I need Kubernetes?**
A: No. The repo ships multiple Docker Compose files; Kubernetes is optional for production scaling.

**Q: Can it run untrusted code safely?**
A: README says it uses `nsjail` sandboxes by default; still treat inputs as untrusted and apply least privilege.

**Q: How do agents interact with it?**
A: Per README: you can build prompt-to-automations from your own agent harness, and tools can integrate with MCP servers.

## Source & Thanks

> Source: https://github.com/TracecatHQ/tracecat
> License: AGPL-3.0
> GitHub stars: 3,598 · forks: 359

---

<!-- ZH -->

## 快速使用

```bash
git clone https://github.com/TracecatHQ/tracecat.git
cd tracecat
cp .env.example .env

# 类生产的本地栈
docker compose -f docker-compose.local.yml up

#（可选）开发栈
docker compose -f docker-compose.dev.yml up
```

## 简介

Tracecat 是开源的安全自动化平台，面向团队与 AI agent：基于 Temporal 的耐久化工作流，配合 nsjail 沙盒执行与集成表格/案例管理，支持 Docker 自托管。

- **适合谁：** 安全工程 / SOC 自动化 / 让 agent 执行 playbook
- **可搭配：** Docker Compose；Temporal；PostgreSQL；可对接外部 MCP servers（见 README）
- **准备时间：** 30–90 分钟

## 实战建议

- GitHub：3,598 stars · 359 forks；最近更新 2026-05-12（GitHub API 验证）。
- 仓库包含 `docker-compose.dev.yml` / `docker-compose.local.yml`，并提供 `justfile` 封装常用命令。
- README：默认用 `nsjail` 沙盒执行；工作流基于 Temporal 做耐久化与重试。

## 主要内容

一个更稳妥的落地路径：

1. **先从一个 playbook 开始。** 选一个高频任务（告警去重、IOC 丰富化、钓鱼分流）把它建成工作流。
2. **对“高风险工具”做闸门。** 任何会改动生产系统/客户数据的动作都先加人审或审批队列。
3. **把脚本当资产管理。** 自定义 Python 工具放在 Git 里，按版本同步进平台。
4. **把 MCP server 当依赖。** 只接入少量、经过审查的 MCP server，并固定配置，保证可复现。

在开发机上试跑时，把密钥放在环境变量并勤轮换；生产建议放到独立环境并使用可审计的凭据。

### FAQ

**一定要上 Kubernetes 吗？**
答：不一定。仓库自带多份 Docker Compose；K8s 更多用于生产扩展。

**能安全运行不可信代码吗？**
答：README 提到默认用 `nsjail` 沙盒；但仍应最小权限、对输入保持不信任。

**agent 怎么接入？**
答：README 表示可从自定义 agent harness 构建自动化，且工具可对接外部 MCP server。

## 来源与感谢

> Source: https://github.com/TracecatHQ/tracecat
> License: AGPL-3.0
> GitHub stars: 3,598 · forks: 359


---
Source: https://tokrepo.com/en/workflows/tracecat-agentic-security-automation
Author: Agent Toolkit