Azure Assistant MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AZURE_ASSISTANT_CONFIG | Yes | Path to the Azure configuration JSON file containing tenant and service principal credentials | |
| AZURE_ASSISTANT_KQL_PATH | No | Override the template directory for KQL templates (optional, defaults to src/azure_assistant_mcp/kql/) |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ask-azureC | Answer a question by generating and running an Azure Resource Graph KQL query. |
| list-tenantsB | List configured tenants from azure-config.json, including optional management group and default subscription info. |
| run-arg-kqlC | Run a provided KQL query against Azure Resource Graph. |
| run-kql-templateC | Execute a KQL template from kql/ by name, with optional {{param}} replacements. |
| vm-count-by-tenantB | Count virtual machines per configured tenant (uses all subscriptions when available). |
| list-subscriptionsC | List subscriptions accessible to the configured service principal for a tenant. |
| arg-tablesC | Overview of common Azure Resource Graph tables, their purpose, and typical use cases. |
| arg-examplesB | Sample KQL snippets for common scenarios across ARG tables. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Most tools have distinct purposes, with clear separation between query execution (run-arg-kql, run-kql-template), information lookup (arg-tables, arg-examples), and administrative tasks (list-subscriptions, list-tenants, vm-count-by-tenant). However, ask-azure overlaps somewhat with run-arg-kql as both execute KQL queries, though ask-azure adds question interpretation.
The naming follows a mostly readable pattern with hyphen-separated words, but there's inconsistency in verb usage: some use action-oriented verbs (run-, list-, ask-), while others are noun-based (arg-examples, arg-tables). This mixed convention reduces predictability across the toolset.
With 8 tools, this server is well-scoped for Azure Resource Graph interactions. Each tool serves a specific function in querying, managing, or learning about Azure resources, and the count feels appropriate without being overwhelming or insufficient for the domain.
The toolset covers core aspects of Azure Resource Graph operations, including query execution, template management, subscription/tenant listing, and educational resources. A minor gap exists in direct resource manipulation (e.g., create or modify resources), but this aligns with the server's focus on querying and analysis rather than full CRUD operations.