Skip to main content
Glama
dstreefkerk

ms-sentinel-mcp-server

by dstreefkerk

sentinel_analytics_rules_count_by_technique

Count Microsoft Sentinel analytics rules by MITRE ATT&CK technique to analyze security coverage and identify gaps in threat detection.

Instructions

Count Sentinel analytics rules by MITRE technique.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kwargsYes

Implementation Reference

  • The async run method that implements the core logic of the tool: retrieves Sentinel analytics rules, extracts MITRE techniques using helper function, aggregates counts and rule summaries per technique, returns structured results or error.
    async def run(self, ctx: Context, **kwargs) -> Dict:
        """
        Count analytics rules by technique.
        Returns a dict: {technique: {count: int, rules: [{id, display_name}]}}
        """
        logger = self.logger
        workspace, resource_group, subscription_id = self.get_azure_context(ctx)
        client = self.get_securityinsight_client(subscription_id)
        technique_map = {}
        try:
            rules = client.alert_rules.list(
                resource_group_name=resource_group,
                workspace_name=workspace,
            )
            for rule in rules:
                rule_dict = rule.as_dict() if hasattr(rule, "as_dict") else dict(rule)
                _, _, techniques = extract_tags_tactics_techniques_from_dict(rule_dict)
                display_name = (
                    rule_dict.get("display_name")
                    or rule_dict.get("displayName")
                    or rule_dict.get("name")
                )
                for technique in techniques or ["Unknown"]:
                    tkey = technique.lower() or "unknown"
                    if tkey not in technique_map:
                        technique_map[tkey] = {"count": 0, "rules": []}
                    technique_map[tkey]["count"] += 1
                    technique_map[tkey]["rules"].append(
                        {
                            "id": rule_dict.get("id"),
                            "display_name": display_name,
                        }
                    )
            return {
                "valid": True,
                "error": None,
                "results": technique_map,
                "errors": [],
            }
        except Exception as e:
            logger.error("Error in %s: %s", self.__class__.__name__, str(e))
            return {
                "valid": False,
                "error": str(e),
                "results": None,
                "errors": [str(e)],
            }
  • The register_tools function that registers the SentinelAnalyticsRulesCountByTechniqueTool (line 621) along with other analytics tools to the MCP server.
    def register_tools(mcp):
        """
        Register all analytics tools with the given MCP server instance.
    
        Args:
            mcp: The MCP server instance to register tools with.
        """
        SentinelAnalyticsRuleListTool.register(mcp)
        SentinelAnalyticsRuleGetTool.register(mcp)
        SentinelAnalyticsRuleTemplatesListTool.register(mcp)
        SentinelAnalyticsRuleTemplateGetTool.register(mcp)
        SentinelAnalyticsRulesCountByTacticTool.register(mcp)
        SentinelAnalyticsRuleTemplatesCountByTacticTool.register(mcp)
        SentinelAnalyticsRulesCountByTechniqueTool.register(mcp)
        SentinelAnalyticsRuleTemplatesCountByTechniqueTool.register(mcp)
  • Tool name and description defining the schema/identity for the MCP tool.
    name = "sentinel_analytics_rules_count_by_technique"
    description = "Count Sentinel analytics rules by MITRE technique."
  • Helper function to extract tags, tactics, and techniques from rule dictionaries, used in the handler to parse MITRE ATT&CK mappings.
    def extract_tags_tactics_techniques_from_dict(obj):
        """
          Extract tags, tactics, and techniques from an analytics rule/template dict.
    
        Args:
            obj (dict): Analytics rule or template dictionary.
    
        Returns:
            tuple: (tags, tactics, techniques)
                tags (list[dict]): All tags as {name, value} pairs.
                tactics (list[str]): List of tactics (from tags or legacy fields).
                techniques (list[str]): 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 = []
        raw_tags = obj.get("tags")
        if raw_tags:
            for tag in raw_tags:
                tag_name = None
                tag_value = None
                if isinstance(tag, dict):
                    tag_name = tag.get("name") or tag.get("Name")
                    tag_value = tag.get("value") or tag.get("Value")
                elif hasattr(tag, "name") and hasattr(tag, "value"):
                    tag_name = getattr(tag, "name", None)
                    tag_value = getattr(tag, "value", None)
                elif isinstance(tag, str):
                    tag_name = tag
                    tag_value = None
                else:
                    try:
                        tag_name = str(tag)
                    except Exception:
                        continue
                if tag_name is not None:
                    tags.append({"name": tag_name, "value": tag_value})
        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()]
        legacy_tactics = obj.get("tactics")
        if legacy_tactics:
            tactics += [
                t.strip() for t in legacy_tactics if isinstance(t, str) and t.strip()
            ]
        legacy_techniques = obj.get("techniques")
        if legacy_techniques:
            techniques += [
                t.strip() for t in legacy_techniques if isinstance(t, str) and t.strip()
            ]
        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
Behavior1/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states what the tool does ('Count...') without explaining how it behaves—e.g., whether it requires authentication, has rate limits, returns aggregated data, or handles errors. This is inadequate for a tool with no annotation coverage.

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 with no wasted words, clearly front-loading the core purpose. It is appropriately sized for a simple counting operation, though its brevity contributes to gaps in other dimensions.

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 fails to explain parameter usage, behavioral traits, or output format, making it insufficient for an agent to use the tool effectively without additional context.

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 required parameter ('kwargs') with 0% description coverage, and the tool description provides no information about parameters. It does not explain what 'kwargs' should contain (e.g., filter criteria, MITRE technique IDs) or its format, leaving the parameter completely undocumented.

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 verb ('Count') and resource ('Sentinel analytics rules') with a specific grouping criterion ('by MITRE technique'), making the purpose unambiguous. It distinguishes from some siblings like 'sentinel_analytics_rule_list' (which lists rules) but not explicitly from 'sentinel_analytics_rules_count_by_tactic' (which counts by tactic instead of technique).

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 does not mention sibling tools like 'sentinel_analytics_rules_count_by_tactic' for counting by tactic or 'sentinel_analytics_rule_list' for listing rules, leaving the agent to infer usage context based on the name alone.

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