data-ai MCP Server
A Model Context Protocol (MCP) server that enables AI assistants to interact with AKS clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and AKS.
Discovered via github-seeds:mcp-hot and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
Optional timeout in seconds (default: 120)
Perform outbound network connectivity check
Stop VM
(`admin` access level):
Private endpoint information
(required): AKS cluster resource ID
(single virtual machines), `vmss` (virtual machine scale sets)
Run a specific AKS diagnostic detector
and Control Plane Availability and Performance
to your MCP configuration file:
Get details of a VM/VMSS
Delete cluster
Upgrade node pool
Network Security Group information
Query AKS control plane logs with safety constraints
Log level filter (`ERROR`, `WARN`, `INFO`)
list, show, get, create, delete
(required for `run` and `run_by_category` operations): Start time in UTC ISO format (within last 30 days)
setting the environment variable `USE_LEGACY_TOOLS=true`.
(all access levels):
Scale node pool
Subnet information
Check if AKS cluster has diagnostic settings configured
Time range for logs (e.g., `1h`, `30m`, `2d`) - takes precedence over `lines`
Start VM
Only read operations are allowed
List node pools in cluster
Update cluster configuration
Get cluster credentials for kubectl access
Unified tool for Azure monitoring and diagnostics operations for AKS clusters.
VMSS name (obtain from `get_aks_vmss_info` or `kubectl get nodes`)
*(available when `USE_LEGACY_TOOLS=true`)*
(`readwrite`/`admin` access levels):
Delete node pool
Virtual Network information
Execute KQL queries against Application Insights telemetry data
Number of recent log lines to return (default: 500, max: 2000)
Get runtime status
list, show, create, start, stop, delete
List Azure subscriptions
Add node pool to cluster
Get information about all network resources
Retrieve resource health events for AKS clusters
Type of logs to collect (`kubelet`, `containerd`, `kernel`, `syslog`)
*(default, available when `USE_LEGACY_TOOLS` is not set or set to `false`)*
Show node pool details
Upgrade Kubernetes version
Unified tool for getting Azure network resource information used by AKS clusters.
Get available Kubernetes versions
Azure authentication
Load Balancer information
Set active subscription
Route Table information
Get detailed VMSS configuration for node pools in the AKS cluster
Filter logs by keyword (case-insensitive text match)
VMSS instance ID
(required): Operation to perform (`list`, `run`, or `run_by_category`)
Identity and Security
Collect system logs from AKS VMSS nodes for debugging and troubleshooting.
one run command can execute at a time per VMSS instance
list, show, create, update, delete
(required for `run` and `run_by_category` operations): End time in UTC ISO format (within last 30 days, max 24h from start)
Generate recommendation reports
Reimage VMSS instances (VM not supported for reimage)
Practices
resource_group, cluster_names, category (Cost,
Run all detectors in a specific category
Issues
(required for `run_by_category` operation): Detector category
**Example Usage:**
Both read and write operations are allowed
must be simple Azure CLI invocations without shell features like pipes (|), redirects (>, <), command substitution, or semicolons (;).
List recommendations with filtering options
Scale cluster node count
(required for `run` operation): Name of the detector to run
Retrieve and manage Azure Advisor recommendations for AKS clusters.
List metric values for resources
Unified tool for managing Azure Virtual Machines (VMs) and Virtual Machine Scale Sets (VMSS) used by AKS.
list, show, create, update, delete, get-credentials
list, show, create, delete
Create new cluster
Comprehensive Azure Fleet management for multi-cluster scenarios.
Health
The complete Azure CLI command to execute (e.g., `az aks list --resource-group myRG`, `az vm list --subscription <sub-id>`)
Unified tool for executing AKS diagnostic detector operations.
Restart VM/VMSS instances