Security Copilot and Sentinel MCP Server
@jguimera
关于 Security Copilot and Sentinel MCP Server
MCP Server that integrates with Security Copilot, Sentinel and other tools (in the future). It enhance the process of developing , testing and uploading Security Copilot artifacts.
基本信息
配置
工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is Security Copilot and Sentinel MCP Server?
A Python-based MCP server using the FastMCP library that provides integration with Microsoft Security Copilot and Microsoft Sentinel via Azure Identity Authentication. It enables running KQL queries against Sentinel, managing Security Copilot skillsets/plugins, and executing prompts and skills, acting as a bridge between development environments and Microsoft Security Copilot.
How to use Security Copilot and Sentinel MCP Server?
Clone the repository, install dependencies with pip install -r requirements.txt, create a .env file with your Azure and Sentinel configuration, then start the server with python server.py. Optionally run tests with python server.py --run-tests. The server exposes tools that can be invoked from MCP clients like Cursor.
Key features of Security Copilot and Sentinel MCP Server
- Execute KQL queries against Microsoft Sentinel workspaces
- List existing skillsets/plugins in Security Copilot
- Upload or update skillsets/plugins
- Run prompts or skills in Security Copilot
- Supports interactive browser, client secret, and managed identity authentication
Use cases of Security Copilot and Sentinel MCP Server
- Develop, test, and deploy Security Copilot KQL skills
- Integrate Sentinel query results into Security Copilot workflows
- Automate management of Security Copilot plugins and prompts
- Enable AI‑assisted security operations via MCP client (e.g., Cursor)
FAQ from Security Copilot and Sentinel MCP Server
What are the prerequisites to run this server?
Python 3.8+, a Microsoft Sentinel workspace, access to Microsoft Security Copilot, and appropriate Azure permissions for both services.
What authentication methods are supported?
Three methods: interactive browser, client secret (using an App Registration), and managed identity.
How do I configure the server?
Create a .env file with your tenant ID, client ID, client secret (optional), Sentinel subscription ID, resource group, workspace name, workspace ID, and authentication type (interactive or client_secret).
What transport does the MCP server use?
The server uses SSE (Server‑Sent Events) as the transport layer.
What tools are provided by the server?
run_sentinel_query, get_skillsets, upload_plugin, and run_prompt.
开发工具 分类下的更多 MCP 服务器
sentry-mcp
getsentryAn MCP server for interacting with Sentry via LLMs.
test
cloudwegoThe ultimate LLM/AI application development framework in Go.
FastAPI-MCP
tadata-orgExpose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
MCP Containers
metorialConnect any AI model to 1200+ integrations (MCP, CLI, API)
Smithery CLI
smithery-aiInstall, manage and develop MCP servers and skills for agents
评论