kubesleuth
by sudhaseeli
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| --live | No | Flag that switches the MCP server to a real cluster instead of a simulated scenario, e.g. `kubesleuth mcp --live --namespace shop --target deployment/checkout-api`. Set to "true" to enable. | |
| --target | No | Target workload to investigate on a live cluster, e.g. "deployment/checkout-api"; used together with --live and --namespace. | |
| --scenario | No | Name of a bundled incident scenario to replay offline, e.g. "oom-kill". Use this for the simulated backend (`kubesleuth mcp --scenario oom-kill`). | |
| --namespace | No | Kubernetes namespace to investigate; used together with --live and --target. | |
| --prometheus | No | Prometheus base URL used to query metrics on a live cluster, e.g. http://localhost:9090 (typically via kubectl port-forward). |
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 |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues