OpenShift MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENSHIFT_CONTEXT | Yes | The OpenShift context name to use | |
| OPENSHIFT_NAMESPACE | Yes | The default namespace to operate in |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| prompts | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| oc_getC | Get OpenShift resources like pods, deploymentconfigs, routes, projects, etc. |
| oc_createC | Create OpenShift resources like projects, deploymentconfigs, routes, etc. |
| oc_install_operatorA | Install an Operator on the OpenShift/Kubernetes cluster using OLM, Helm, or direct manifests |
| oc_new_appB | Create a new application from a GitHub repository using S2I build and expose it with an edge-terminated route |
| oc_scaleA | Scale the number of pods in a deployment, deploymentconfig, replicaset, or statefulset to the specified number of replicas |
| oc_describeB | Describe any OpenShift resource and share the output in various formats including human-readable summary |
| oc_applyC | Apply YAML manifests to OpenShift cluster with comprehensive error handling and validation for all scenarios |
| oc_deleteB | Delete OpenShift resources with comprehensive safety checks, validation, and error handling |
| oc_logsB | Get logs from OpenShift resources like pods, deployments, builds, etc. with advanced filtering and streaming options |
| oc_patchC | Patch OpenShift resources with strategic merge, JSON merge, or JSON patch operations |
| oc_loginB | Securely log into an OpenShift cluster using username/password or token authentication |
| oc_api_resourcesA | List all available API resources in the OpenShift cluster with their details |
| oc_explainB | Explain OpenShift/Kubernetes resource schemas, fields, and API documentation |
| oc_exposeC | Expose an OpenShift resource (service, deployment, etc.) with secure route endpoints supporting SSL/TLS termination |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| troubleshoot-openshift-prompt | Comprehensive OpenShift troubleshooting guide covering pods, deployments, services, routes, builds, and cluster-wide issues |
| monitoring-prompts | Comprehensive monitoring and observability guidance for OpenShift clusters covering metrics, logging, alerting, and performance analysis |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| OpenShift Cluster Information | Comprehensive information about the OpenShift cluster including version, nodes, and status |
| OpenShift Project List | Comprehensive list of all projects/namespaces with detailed information, quotas, and usage statistics |
| OpenShift Application Templates | Comprehensive collection of application deployment templates for common OpenShift scenarios and frameworks |
TDQS
Scored across 14 tools
Each tool maps to a distinct OpenShift operation (get vs. describe vs. create vs. apply, etc.) with clear boundaries. The functions are well-separated and unlikely to be confused.
All tools follow a consistent oc_ prefix with snake_case verb or noun forms (e.g., oc_describe, oc_new_app, oc_api_resources). The naming pattern is uniform and predictable.
14 tools is well within the ideal range for a domain-specific server covering common OpenShift operations. Each tool serves a necessary purpose without redundancy.
The set covers the full lifecycle: authentication (login), resource discovery (api_resources, explain), creation/updating (create, apply, patch, new_app), inspection (get, describe, logs), scaling, exposure, and deletion. Operators are also supported. No critical gaps for typical cluster management.