mcpField
M
Microsoft Sentinel Data Exploration

Microsoft Sentinel Data Exploration

Remote
github.comSecurity1Updated 41w ago

About Microsoft Sentinel Data Exploration

Microsoft Sentinel Data Exploration lets compatible clients search for relevant tables and retrieve data from the Sentinel data lake using natural language. It is intended for agents and security workflows that need to explore security data.

Key features

  1. 01Searches for relevant Sentinel tables
  2. 02Retrieves data from the Sentinel data lake
  3. 03Accepts natural-language queries
  4. 04Supports OAuth 2.0 authentication

Use cases

  1. 01Select sign-in tables for password-spray hunts
  2. 02Correlate login events for impossible travel checks
  3. 03Analyze multi-factor authentication failures
  4. 04Find dormant accounts with recent activity

MCP support

This remote MCP server exposes tools for finding relevant Microsoft Sentinel data-lake tables and retrieving data to MCP-compatible clients. Connect through its endpoint using OAuth 2.0.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://sentinel.microsoft.com/mcp/data-exploration
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Microsoft Sentinel Data Exploration

INSTALL Install Microsoft Sentinel Data Exploration MCP in VS Code Install Microsoft Sentinel Data Exploration MCP in VS Code Insiders

The data exploration tool collection in the Microsoft Sentinel MCP server lets you search for relevant tables and retrieve data from Microsoft Sentinel's data lake using natural language.

🌐 The Microsoft Sentinel Data Exploration MCP Server Endpoint

The Microsoft Sentinel Data Exploration MCP Server is accessible to any IDE, agent, or tool that supports the Model Context Protocol (MCP). Any compatible client can connect to the following remote MCP endpoint:

https://sentinel.microsoft.com/mcp/data-exploration

Authentication OAuth 2.0

🧩 Use cases

Password-Spray Hunt Build security agents that autonomously select relevant sign-in tables, aggregates login attempts by user and IP, and flags patterns consistent with password-spray behavior—like low-frequency attempts over several months across many accounts.

Impossible Travel Check Build security agents that correlate sign-in events by user, calculates geodistance and time gaps between logins, and flags cases where travel speed exceeds realistic thresholds, suggesting credential compromise.

Multi-factor authorization failures Build security agents that analyzes multi-factor auth logs to detect spikes in failure rates, clustering by user, IP, or time window, and surfaces anomalies that deviate from baseline behavior over long periods.

Dormant Account wake-up Build security agents that based on inactivity thresholds, scans for accounts with long silence followed by recent activity, and builds a timeline showing when and how these accounts re-engaged.

📚 Learn more

Explore Microsoft Sentinel data lake with data exploration collection

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.