Skip to main content
Glama
dstreefkerk

ms-sentinel-mcp-server

by dstreefkerk

sentinel_hunting_queries_count_by_tactic

Count Microsoft Sentinel hunting queries by MITRE ATT&CK tactic to analyze security coverage and identify gaps in threat detection.

Instructions

Count Sentinel hunting queries (saved searches) by tactic

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kwargsYes

Implementation Reference

  • The main handler class for the tool. It defines the tool name, description, and the async run method that lists Sentinel saved searches, extracts tactics using the helper function, and returns a dictionary mapping tactics to counts and associated query IDs.
    class SentinelHuntingQueriesCountByTacticTool(MCPToolBase):
        name = "sentinel_hunting_queries_count_by_tactic"
        description = "Count Sentinel hunting queries (saved searches) by tactic"
    
        async def run(self, ctx: Context, **_):
            """
            Count Sentinel hunting queries (saved searches) by tactic.
            Extracts tags, tactics, and techniques using shared utility.
            """
            workspace_name, resource_group, subscription_id = self.get_azure_context(ctx)
            client = self.get_loganalytics_client(subscription_id)
            tactic_map = {}
            try:
                searches = client.saved_searches.list_by_workspace(
                    resource_group, workspace_name
                )
                for s in getattr(searches, "value", []):
                    _, s_tactics, _ = extract_tags_tactics_techniques(s)
                    for tactic in s_tactics or ["Unknown"]:
                        tkey = tactic.lower() or "unknown"
                        if tkey not in tactic_map:
                            tactic_map[tkey] = {"count": 0, "queries": []}
                        tactic_map[tkey]["count"] += 1
                        tactic_map[tkey]["queries"].append(
                            {
                                "id": s.id,
                                "display_name": getattr(s, "display_name", s.name),
                            }
                        )
                return {
                    "valid": True,
                    "error": None,
                    "results": tactic_map,
                    "errors": [],
                }
            except Exception as e:
                self.logger.error("Error in %s: %s", self.__class__.__name__, str(e))
                return {
                    "valid": False,
                    "error": str(e),
                    "results": None,
                    "errors": [str(e)],
                }
  • Function that registers the hunting tools with the MCP server, including the register call for SentinelHuntingQueriesCountByTacticTool.
    def register_tools(mcp: FastMCP):
        SentinelHuntingQueriesListTool.register(mcp)
        SentinelHuntingQueriesCountByTacticTool.register(mcp)
        SentinelHuntingQueryGetTool.register(mcp)
  • Utility function used by the tool to extract tactics (and tags/techniques) from Sentinel saved search objects for categorization.
    def extract_tags_tactics_techniques(obj):
        """
        Extracts tags, tactics, and techniques from a hunting query object.
        Returns:
            tags: List of {name, value} dicts.
            tactics: List of tactics (from tags or legacy fields).
            techniques: List of techniques (from tags or legacy fields).
        Extraction precedence:
          - Tactics/techniques: Prefer tags with name 'tactics'/'techniques'
            (case-insensitive, split on comma). Fallback to legacy fields.
          - Tags: All tags as {name, value} pairs (robust to SDK object, dict, or string).
        """
        tags = []
        tactics = []
        techniques = []
        # Extract tags as list of {name, value}
        raw_tags = getattr(obj, "tags", None)
        if raw_tags:
            for tag in raw_tags:
                tag_name = None
                tag_value = None
                # Tag as dict
                if isinstance(tag, dict):
                    tag_name = tag.get("name") or tag.get("Name")
                    tag_value = tag.get("value") or tag.get("Value")
                # Tag as object with .name/.value
                elif hasattr(tag, "name") and hasattr(tag, "value"):
                    tag_name = getattr(tag, "name", None)
                    tag_value = getattr(tag, "value", None)
                # Tag as string: treat as name only
                elif isinstance(tag, str):
                    tag_name = tag
                    tag_value = None
                # Fallback: try string conversion
                else:
                    try:
                        tag_name = str(tag)
                    except Exception:
                        continue
                if tag_name is not None:
                    tags.append({"name": tag_name, "value": tag_value})
        # Tactics/techniques from tags (case-insensitive match)
        for tag in tags:
            if tag["name"] and isinstance(tag["name"], str):
                if tag["name"].lower() == "tactics" and tag["value"]:
                    tactics += [t.strip() for t in tag["value"].split(",") if t.strip()]
                elif tag["name"].lower() == "techniques" and tag["value"]:
                    techniques += [t.strip() for t in tag["value"].split(",") if t.strip()]
        # Fallback: legacy fields
        legacy_tactics = getattr(obj, "tactics", None)
        if legacy_tactics:
            tactics += [
                t.strip() for t in legacy_tactics if isinstance(t, str) and t.strip()
            ]
        legacy_techniques = getattr(obj, "techniques", None)
        if legacy_techniques:
            techniques += [
                t.strip() for t in legacy_techniques if isinstance(t, str) and t.strip()
            ]
        # Deduplicate and preserve order
        tactics = list(dict.fromkeys([t for t in tactics if t]))
        techniques = list(dict.fromkeys([t for t in techniques if t]))
        return tags, tactics, techniques
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must fully disclose behavioral traits. It states the tool counts queries by tactic, implying a read-only aggregation operation, but lacks details on permissions, rate limits, output format, or error handling. For a tool with zero annotation coverage, this is insufficient to guide safe and effective use.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It is appropriately sized and front-loaded, with zero waste, making it easy for an agent to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (a counting operation with a parameter), lack of annotations, 0% schema coverage, and no output schema, the description is incomplete. It doesn't cover parameter usage, behavioral context, or output details, leaving significant gaps for the agent to infer or fail.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has one parameter ('kwargs') with 0% description coverage, and the tool description provides no information about parameters. It doesn't explain what 'kwargs' should contain, its format, or how it influences the count. This leaves the parameter undocumented, failing to compensate for the schema gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Count Sentinel hunting queries (saved searches) by tactic.' It specifies the verb ('count'), resource ('Sentinel hunting queries'), and grouping dimension ('by tactic'). However, it doesn't explicitly differentiate from siblings like 'sentinel_hunting_queries_list' or 'sentinel_analytics_rules_count_by_tactic,' which would be needed for a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, context, or exclusions, nor does it reference sibling tools like 'sentinel_hunting_queries_list' for listing queries or 'sentinel_analytics_rules_count_by_tactic' for counting analytics rules. This leaves the agent without usage direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/dstreefkerk/ms-sentinel-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server