azure-query-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AZURE_CLIENT_ID | No | Azure client (application) ID for service principal authentication. | |
| AZURE_TENANT_ID | No | Microsoft Entra tenant ID to use for authentication. Also used when authenticating via Azure CLI. | |
| AZURE_CLIENT_SECRET | No | Azure client secret for service principal authentication. Avoid placing directly in committed MCP configuration; use the host's secret store or managed identity. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_workspacesA | List Azure Log Analytics workspaces accessible in a subscription. |
| search_tablesA | List or search tables in a Log Analytics workspace using ARM metadata. |
| describe_tableA | Get the canonical schema and retention metadata for a Log Analytics table. |
| query_workspaceA | Use for telemetry, logs, events, metrics, and time-series data stored in a Log Analytics workspace. Run bounded, read-only KQL against one workspace. Do not use for Azure resource inventory or configuration; use query_azure_resources for those. |
| query_azure_resourcesA | Use for Azure resource inventory, configuration, tags, policy, health, and cross-subscription discovery through Azure Resource Graph. Do not use for telemetry, logs, events, or time-series analysis; use query_workspace for those. |
| list_incidentsA | List Microsoft Sentinel incidents (latest state of each) from the SecurityIncident table, newest first. Use to find incidents to triage; then call get_incident for details. |
| get_incidentA | Get one Microsoft Sentinel incident with its alerts and the account, IP and host entities involved. Returned pivotEntities can be passed directly to entity_timeline; unresolvedEntities lists entities recorded without a usable identifier (for example only a display name or SID). |
| entity_timelineA | Build a cross-source activity timeline for one account (UPN), IP address or host: sign-ins, audit events, Office activity, endpoint telemetry, firewall logs and alerts. Tables that are not ingested are skipped automatically. |
| check_ingestion_healthA | Check whether log data is still arriving: per-table last-seen time, 24h volume versus the previous daily average, stale tables, volume drops or spikes, and ingestion latency over the last hour. |
| list_hunting_queriesA | List the available threat-hunting queries (built-in plus any loaded from AZURE_QUERY_MCP_HUNTING_DIR) with their MITRE ATT&CK tactics and techniques. |
| run_hunting_queryA | Run one hunting query from list_hunting_queries against a workspace. Results are capped at 1,000 rows. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| triage_incident | Walk through an incident: details, alerts, entity timelines, and a verdict with next steps. |
| ingestion_health_review | Review log ingestion health and explain any stale tables, volume changes or latency. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
Tools are cleanly partitioned by intent, and the two most conflict-prone tools (query_workspace vs query_azure_resources) explicitly exclude each other's use cases in their descriptions. Incident tools (list vs get) and table tools (search_tables vs describe_table) are clearly separated, and entity_timeline is framed as a cross-source pivot rather than a generic query.
Nearly all tools follow a verb_noun pattern (list_incidents, get_incident, run_hunting_query, check_ingestion_health, describe_table, search_tables). The lone deviation, entity_timeline, is a noun-only name but remains readable and unambiguous in context.
Eleven tools is well within the ideal range for a security/telemetry server, and each maps to a distinct stage of the workflow (discovery, querying, schema introspection, incident triage, hunting, health checks). No tool appears redundant or filler.
The read-only surface covers workspace/table discovery, KQL querying, resource graph inventory, ingestion health, incident retrieval, entity timelines, and hunting queries with good lifecycle coherence. The main gap is incident write-back — the description says list_incidents is for finding incidents to triage, but there is no update_incident to assign, comment, or close one.