caldera-mcp
Connects MCP-compatible AI clients to a MITRE Caldera adversary emulation platform, enabling natural language construction of attack scenarios, agent inspection, and operation management.
README
caldera-mcp
MCP server for MITRE Caldera adversary emulation platform.
Connects any MCP-compatible AI client (Claude, Cursor, VS Code, etc.) to a running Caldera instance. Build attack scenarios from natural language, inspect connected agents, and manage operations — all through conversation.
Important: This tool connects an AI to a live adversary emulation platform. Only point it at Caldera instances you own and are authorized to operate. Always review scope before executing any operation.
Tools (17)
| Group | Tools |
|---|---|
| Health | caldera_health_check |
| Agents | caldera_list_agents, caldera_get_agent |
| Abilities | caldera_list_abilities, caldera_get_ability, caldera_create_ability, caldera_delete_ability |
| Adversaries | caldera_list_adversaries, caldera_get_adversary, caldera_create_adversary, caldera_update_adversary, caldera_delete_adversary |
| Operations | caldera_list_operations, caldera_get_operation, caldera_create_operation, caldera_set_operation_state, caldera_get_operation_results, caldera_delete_operation |
Key behaviors:
caldera_list_abilitiessupports filters:technique_id,tactic,platformcaldera_create_operationdefaults tostate="paused"— operations never start automatically- Input validation enforced on technique IDs (ATT&CK format), platforms, and executors
Requirements
- Python 3.12+ or Docker
- A running MITRE Caldera instance (v5.x)
- The Caldera red team API key
Installation
uvx — zero install (recommended)
Requires uv.
CALDERA_URL=http://my-caldera:8888 \
CALDERA_API_KEY=your-red-api-key \
uvx caldera-mcp
pip
pip install caldera-mcp
CALDERA_URL=http://my-caldera:8888 CALDERA_API_KEY=your-red-api-key caldera-mcp
Docker (SSE / server mode)
docker run --rm \
-e CALDERA_URL=http://my-caldera:8888 \
-e CALDERA_API_KEY=your-red-api-key \
-p 8081:8081 \
ghcr.io/cowboy-samurai/caldera-mcp \
--transport sse
Configuration
| Variable | Required | Default | Description |
|---|---|---|---|
CALDERA_API_KEY |
Yes | — | Caldera red team API key |
CALDERA_URL |
No | http://localhost:8888 |
Caldera server base URL |
The red team API key can be found in your Caldera config (conf/local.yml → api_key_red), or in the container logs if auto-generated.
MCP client setup
Claude Code
Add to .mcp.json in your project root:
{
"mcpServers": {
"caldera": {
"command": "uvx",
"args": ["caldera-mcp"],
"env": {
"CALDERA_URL": "http://my-caldera:8888",
"CALDERA_API_KEY": "your-red-api-key"
}
}
}
}
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"caldera": {
"command": "uvx",
"args": ["caldera-mcp"],
"env": {
"CALDERA_URL": "http://my-caldera:8888",
"CALDERA_API_KEY": "your-red-api-key"
}
}
}
}
SSE mode (remote Caldera)
If your Caldera instance is remote and you want the MCP server to run as a persistent process:
caldera-mcp --transport sse --host 127.0.0.1 --port 8081
Then configure your client to connect via SSE:
{
"mcpServers": {
"caldera": {
"type": "sse",
"url": "http://localhost:8081/sse"
}
}
}
Usage examples
Once connected, talk to your AI client naturally:
List all alive agents
Find abilities for T1059.001 on Windows
Create an adversary from these techniques: T1566.001, T1059.001, T1003.001
What operations are currently running?
Operations created through this server default to
pausedstate. Always review scope — techniques, commands, and targeted hosts — before resuming any operation.
License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。