Aks MCP
未认领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.
安装
<path of binary aks-mcp>更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
40 个工具中显示 40 个
文档中列出的工具 (40)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
Admin-Only
(admin access level):
aks_resource_id
AKS cluster resource ID
all
Get information about all network resources
app_insights
Execute KQL queries against Application Insights telemetry data
category
(required for runbycategory operation): Detector category
cli_command
The complete Azure CLI command to execute (e.g., az aks list --resource-group myRG, az vm list --subscription <sub-id>)
control_plane_logs
Query AKS control plane logs with safety constraints
deploy
Deploy Inspektor Gadget to the cluster (via the AKS cluster extension)
detector_name
(required for run operation): Name of the detector to run
diagnostics
Check if AKS cluster has diagnostic settings configured
end_time
(required for run and runbycategory operations): End time in UTC ISO format (within last 30 days, max 24h from start)
filter
Filter logs by keyword (case-insensitive text match)
get-instance-view
Get runtime status
instance_id
VMSS instance ID
kubectl_metadata
Metadata management (label, annotate, set)
kubectl_workloads
Workload lifecycle (run, expose, scale, autoscale, rollout)
level
Log level filter (ERROR, WARN, INFO)
lines
Number of recent log lines to return (default: 500, max: 2000)
load_balancer
Load Balancer information
log_type
Type of logs to collect (kubelet, containerd, kernel, syslog)
metrics
List metric values for resources
nsg
Network Security Group information
operation
(required): Operation to perform (list, run, or runbycategory)
private_endpoint
Private endpoint information
Read-Only
(all access levels):
Read-Write
(readwrite/admin access levels):
readonly
Only read operations are allowed
reimage
Reimage VMSS instances (VM not supported for reimage)
report
Generate recommendation reports
resource_health
Retrieve resource health events for AKS clusters
restart
Restart VM/VMSS instances
route_table
Route Table information
run
Run a specific AKS diagnostic detector
run_by_category
Run all detectors in a specific category
since
Time range for logs (e.g., 1h, 30m, 2d) - takes precedence over lines
start_time
(required for run and runbycategory operations): Start time in UTC ISO format (within last 30 days)
subnet
Subnet information
timeout
Optional timeout in seconds (default: 120)
vmss_name
VMSS name (obtain from getaksvmssinfo or kubectl get nodes)
vnet
Virtual Network information