Aks Mcp

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.

VerifiedReviewed
data-aidata-ai
7 views134 stars38 forksMIT

Why This Matters

Discovered via github-seeds:mcp-hot and last synced 3mo ago.

VerifiedReviewed
Source
github-seeds:mcp-hot
Stars
134
Last synced
3mo ago
Install
Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions
86
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (86)

timeout

Optional timeout in seconds (default: 120)

check-network

Perform outbound network connectivity check

stop

Stop VM

Admin-Only

(`admin` access level):

private_endpoint

Private endpoint information

aks_resource_id

(required): AKS cluster resource ID

vm

(single virtual machines), `vmss` (virtual machine scale sets)

run

Run a specific AKS diagnostic detector

Cluster

and Control Plane Availability and Performance

parameter

to your MCP configuration file:

show

Get details of a VM/VMSS

delete

Delete cluster

nodepool-upgrade

Upgrade node pool

nsg

Network Security Group information

control_plane_logs

Query AKS control plane logs with safety constraints

level

Log level filter (`ERROR`, `WARN`, `INFO`)

ClusterResourcePlacement Operations

list, show, get, create, delete

start_time

(required for `run` and `run_by_category` operations): Start time in UTC ISO format (within last 30 days)

by

setting the environment variable `USE_LEGACY_TOOLS=true`.

Read-Only

(all access levels):

nodepool-scale

Scale node pool

subnet

Subnet information

diagnostics

Check if AKS cluster has diagnostic settings configured

since

Time range for logs (e.g., `1h`, `30m`, `2d`) - takes precedence over `lines`

start

Start VM

readonly

Only read operations are allowed

nodepool-list

List node pools in cluster

update

Update cluster configuration

get-credentials

Get cluster credentials for kubectl access

aks_monitoring

Unified tool for Azure monitoring and diagnostics operations for AKS clusters.

vmss_name

VMSS name (obtain from `get_aks_vmss_info` or `kubectl get nodes`)

az_aks_operations

*(available when `USE_LEGACY_TOOLS=true`)*

Read-Write

(`readwrite`/`admin` access levels):

nodepool-delete

Delete node pool

vnet

Virtual Network information

app_insights

Execute KQL queries against Application Insights telemetry data

lines

Number of recent log lines to return (default: 500, max: 2000)

get-instance-view

Get runtime status

Update Run Operations

list, show, create, start, stop, delete

account-list

List Azure subscriptions

nodepool-add

Add node pool to cluster

all

Get information about all network resources

resource_health

Retrieve resource health events for AKS clusters

log_type

Type of logs to collect (`kubelet`, `containerd`, `kernel`, `syslog`)

call_az

*(default, available when `USE_LEGACY_TOOLS` is not set or set to `false`)*

nodepool-show

Show node pool details

upgrade

Upgrade Kubernetes version

aks_network_resources

Unified tool for getting Azure network resource information used by AKS clusters.

get-versions

Get available Kubernetes versions

login

Azure authentication

load_balancer

Load Balancer information

account-set

Set active subscription

route_table

Route Table information

get_aks_vmss_info

Get detailed VMSS configuration for node pools in the AKS cluster

filter

Filter logs by keyword (case-insensitive text match)

instance_id

VMSS instance ID

operation

(required): Operation to perform (`list`, `run`, or `run_by_category`)

Deprecations

Identity and Security

collect_aks_node_logs

Collect system logs from AKS VMSS nodes for debugging and troubleshooting.

Only

one run command can execute at a time per VMSS instance

Member Operations

list, show, create, update, delete

end_time

(required for `run` and `run_by_category` operations): End time in UTC ISO format (within last 30 days, max 24h from start)

report

Generate recommendation reports

reimage

Reimage VMSS instances (VM not supported for reimage)

Best

Practices

Filter Options

resource_group, cluster_names, category (Cost,

run_by_category

Run all detectors in a specific category

Connectivity

Issues

category

(required for `run_by_category` operation): Detector category

Storage

**Example Usage:**

readwrite/admin

Both read and write operations are allowed

Commands

must be simple Azure CLI invocations without shell features like pipes (|), redirects (>, <), command substitution, or semicolons (;).

list

List recommendations with filtering options

scale

Scale cluster node count

detector_name

(required for `run` operation): Name of the detector to run

aks_advisor_recommendation

Retrieve and manage Azure Advisor recommendations for AKS clusters.

metrics

List metric values for resources

az_compute_operations

Unified tool for managing Azure Virtual Machines (VMs) and Virtual Machine Scale Sets (VMSS) used by AKS.

Fleet Operations

list, show, create, update, delete, get-credentials

Update Strategy Operations

list, show, create, delete

create

Create new cluster

az_fleet

Comprehensive Azure Fleet management for multi-cluster scenarios.

Node

Health

cli_command

The complete Azure CLI command to execute (e.g., `az aks list --resource-group myRG`, `az vm list --subscription <sub-id>`)

aks_detector

Unified tool for executing AKS diagnostic detector operations.

restart

Restart VM/VMSS instances