List and filter Microsoft Sentinel detection rules (analytics) - search by solution, severity, tactic, technique, name, query content, or file path. Returns max 100 results by default.
AI agents call list_detections to retrieve information from Sentinel Solutions MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and searches metadata about Microsoft Sentinel detection rules from repositories. It performs read-only queries against an indexed dataset of security content without executing code, modifying data, or triggering external operations. The maximum 100 results return and search filtering confirm this is a passive data retrieval function suitable for discovery and analysis purposes.
From the tool's definition Tool name 'list_detections' and description explicitly states it 'List and filter' detection rules, with search/filter parameters (solution, severity, tactic, technique, name, query content, file path) and 'Returns max 100 results'.
Attacks that exploit this kind of access
List and filter Microsoft Sentinel detection rules (analytics) - search by solution, severity, tactic, technique, name, query content, or file path. Returns max 100 results by default. It is categorised as a Read tool in the Sentinel Solutions MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Sentinel Solutions MCP Server MCP server in PolicyLayer and add a rule for list_detections: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Sentinel Solutions MCP Server. Nothing to install.
list_detections is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_detections rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_detections. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_detections is provided by the Sentinel Solutions MCP Server MCP server (noodlemctwoodle/sentinel-solutions-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →