Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

OpenShift MCP Server

NPM · MCP-SERVER-OPENSHIFT · 2 COMPONENTS · SCANNED SEP 20

OpenShift/Kubernetes cluster management via the oc CLI for MCP clients

0 this week 72 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security80
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects @modelcontextprotocol/sdk 0.7.0, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 8 of 18 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability75
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 3050 tokens (~179/item across 17 items; 14 tools + 3 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
  • Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "oc_delete" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
Install

How do I install the OpenShift MCP Server server?

OpenShift MCP Server runs locally as an npm package, launched with npx -y mcp-server-openshift. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · mcp-server-openshift

# add to Claude Code
claude mcp add sanjaypsachdev-mcp-server-openshift -- npx -y mcp-server-openshift
// .cursor/mcp.json
{
  "mcpServers": {
    "sanjaypsachdev-mcp-server-openshift": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-openshift"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "sanjaypsachdev-mcp-server-openshift": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-openshift"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add sanjaypsachdev-mcp-server-openshift -- npx -y mcp-server-openshift
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sanjaypsachdev-mcp-server-openshift": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mcp-server-openshift"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add sanjaypsachdev-mcp-server-openshift --command npx --arg -y --arg mcp-server-openshift
# ~/.hermes/config.yaml
mcp_servers:
  sanjaypsachdev-mcp-server-openshift:
    command: "npx"
    args: ["-y", "mcp-server-openshift"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "sanjaypsachdev-mcp-server-openshift": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "mcp-server-openshift"
      ]
    }
  }
}
# add to Vellum
assistant mcp add sanjaypsachdev-mcp-server-openshift -t stdio -c npx -a -y mcp-server-openshift
// mcp.json
{
  "mcpServers": {
    "sanjaypsachdev-mcp-server-openshift": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-openshift"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 16 Sept 26 +1
    • Stability: 0.97 → pass security
  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 9 Sept 26 +1
    • Stability: 0.97 → pass security
  • 7 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/mcp-server-openshift@1.2.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 1 finding
ID CVE Severity Vector Fix available
GHSA-w48q-cv73-mx4w CVE-2025-66414 high yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 18 packages
Packages resolved 18
Stale 8
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 14 exposed · ~2,982 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
oc_api_resources ~136

List all available API resources in the OpenShift cluster with their details

NameTypeReqDescription
apiGroupstringFilter by specific API group (e.g., apps, extensions, networking.k8s.io)
categoriesbooleanGroup resources by categories (core, apps, networking, etc.)
contextstringOpenShift context to use (optional)
namespacedbooleanFilter by namespaced resources only
outputstringOutput format for the API resources list
verbsarrayFilter by supported verbs (e.g., ["get", "list", "create", "delete"])

No output schema declared.

No examples provided.

oc_apply ~291

Apply YAML manifests to OpenShift cluster with comprehensive error handling and validation for all scenarios

NameTypeReqDescription
cascadestringDeletion cascade strategy
contextstringOpenShift context to use (optional)
dryRunbooleanValidate only, don't apply (client or server)
fieldManagerstringField manager name for server-side apply
filenamestringPath to YAML file to apply
forcebooleanForce apply, ignore conflicts
gracePeriodnumberGrace period for resource deletion (seconds)
kustomizebooleanApply kustomization directory
manifeststringYAML manifest content to apply
namespacestringOpenShift namespace/project
overwritebooleanOverwrite existing resources
prunebooleanPrune resources not in current configuration
pruneWhitelistarrayResource types to include in pruning
recursivebooleanProcess directory recursively
selectorstringLabel selector for pruning
serverSideApplybooleanUse server-side apply
timeoutstringTimeout for wait operation (e.g., "60s", "5m")
urlstringURL to YAML manifest to apply
validatebooleanValidate resources before applying
waitbooleanWait for resources to be ready

No output schema declared.

No examples provided.

oc_create ~189

Create OpenShift resources like projects, deploymentconfigs, routes, etc.

NameTypeReqDescription
contextstringOpenShift context to use (optional)
descriptionstringDescription for project
displayNamestringDisplay name for project
dryRunbooleanValidate only, don't create
filenamestringPath to YAML file to create resources from
hostnamestringHostname for route
imagestringContainer image for deploymentconfig
manifeststringYAML manifest to create resources from
namestringName of the resource
namespacestringOpenShift namespace/project
replicasnumberNumber of replicas
resourceTypestringType of resource to create (project, deploymentconfig, route, service, etc.)
servicestringService name for route

No output schema declared.

No examples provided.

oc_delete ~308

Delete OpenShift resources with comprehensive safety checks, validation, and error handling

NameTypeReqDescription
allbooleanDelete all resources of the specified type
allNamespacesbooleanDelete resources across all namespaces
cascadestringDeletion cascade strategy
confirmbooleanRequire explicit confirmation for destructive operations
contextstringOpenShift context to use (optional)
dryRunbooleanShow what would be deleted without actually deleting
fieldSelectorstringDelete resources matching field selector
filenamestringPath to YAML file to delete resources from
forcebooleanForce deletion (bypass finalizers)
gracePeriodSecondsnumberGrace period for deletion in seconds
ignore404booleanIgnore 404 errors if resource does not exist
labelSelectorstringDelete resources matching label selector
manifeststringYAML manifest defining resources to delete
namestringName of the resource to delete
namespacestringOpenShift namespace/project
recursivebooleanProcess directory recursively
resourceTypestringType of resource to delete (required if not using manifest/filename)
timeoutstringTimeout for deletion operation (e.g., "60s", "5m")
urlstringURL to YAML manifest defining resources to delete
waitbooleanWait for deletion to complete

No output schema declared.

No examples provided.

oc_describe ~114

Describe any OpenShift resource and share the output in various formats including human-readable summary

NameTypeReqDescription
contextstringOpenShift context to use (optional)
namestringyesName of the resource to describe
namespacestringOpenShift namespace/project
outputstringOutput format: text (default oc describe), yaml, json, or human-readable (concise summary)
resourceTypestringyesType of resource to describe (pod, deployment, service, route, etc.)

No output schema declared.

No examples provided.

oc_explain ~135

Explain OpenShift/Kubernetes resource schemas, fields, and API documentation

NameTypeReqDescription
apiVersionstringSpecific API version to explain (e.g., apps/v1, route.openshift.io/v1)
contextstringOpenShift context to use (optional)
fieldstringSpecific field path to explain (e.g., spec.containers, metadata.labels)
outputstringOutput format for the explanation
recursivebooleanShow all fields recursively
resourcestringyesResource type to explain (e.g., pod, deployment, service, route.route.openshift.io)

No output schema declared.

No examples provided.

oc_expose ~377

Expose an OpenShift resource (service, deployment, etc.) with secure route endpoints supporting SSL/TLS termination

NameTypeReqDescription
annotationsarrayAnnotations to apply to the route in KEY=VALUE format
caCertificatestringPath to CA certificate file
certificatestringPath to TLS certificate file
contextstringOpenShift context to use (optional)
destinationCaCertificatestringPath to destination CA certificate file (for reencrypt)
dryRunbooleanShow what would be created without actually creating it
hostnamestringCustom hostname for the route
insecureEdgeTerminationPolicystringPolicy for insecure traffic: None (reject), Allow (allow), Redirect (redirect to secure)
keystringPath to TLS private key file
labelsarrayLabels to apply to the route in KEY=VALUE format
namestringyesName of the resource to expose
namespacestringOpenShift namespace/project
pathstringPath for the route (e.g., /api)
portstringTarget port to expose (port name or number)
resourceTypestringyesResource type to expose (service, deploymentconfig, deployment)
routeNamestringName for the route (if not specified, derives from resource name)
routeTypestringType of secure route: edge (SSL termination at router), passthrough (SSL passthrough), reencrypt (SSL re-encryption)
tlsTerminationstringTLS termination type (deprecated, use routeType instead)
weightnumberWeight for this route (0-256)
wildcardPolicystringWildcard policy for the route

No output schema declared.

No examples provided.

oc_get ~153

Get OpenShift resources like pods, deploymentconfigs, routes, projects, etc.

NameTypeReqDescription
allNamespacesbooleanList resources across all namespaces
contextstringOpenShift context to use (optional)
fieldSelectorstringFilter resources by field selector
labelSelectorstringFilter resources by label selector (e.g., app=nginx)
namestringName of the resource (optional - if not provided, lists all resources)
namespacestringOpenShift namespace/project
outputstringOutput format
resourceTypestringyesType of resource to get (e.g., pods, deploymentconfigs, routes, projects, services)

No output schema declared.

No examples provided.

oc_install_operator ~216

Install an Operator on the OpenShift/Kubernetes cluster using OLM, Helm, or direct manifests

NameTypeReqDescription
channelstringUpdate channel for the operator (stable, alpha, beta, etc.)
contextstringOpenShift context to use (optional)
createNamespacebooleanCreate namespace if it does not exist
helmRepostringHelm repository URL (required if source is helm)
installPlanApprovalstringInstall plan approval strategy for OLM
manifestUrlstringURL to operator manifest (required if source is manifest)
namespacestringTarget namespace for operator installation
operatorNamestringyesName of the operator to install (e.g., "prometheus-operator", "cert-manager")
sourcestringInstallation method: olm (Operator Lifecycle Manager), helm (Helm chart), or manifest (direct YAML)
versionstringVersion of the operator to install (if not specified, installs latest available)

No output schema declared.

No examples provided.

oc_login ~189

Securely log into an OpenShift cluster using username/password or token authentication

NameTypeReqDescription
authMethodstringyesAuthentication method to use
certificateAuthoritystringPath to certificate authority file for TLS verification
contextstringContext name to save the login session (optional)
insecureSkipTlsVerifybooleanSkip TLS certificate verification (not recommended for production)
namespacestringDefault namespace to set after login
passwordstringPassword for password authentication (required if authMethod is password)
serverstringyesOpenShift cluster server URL (e.g., https://api.cluster.example.com:6443)
timeoutnumberLogin timeout in seconds
tokenstringOpenShift authentication token (required if authMethod is token)
usernamestringUsername for password authentication (required if authMethod is password)

No output schema declared.

No examples provided.

oc_logs ~261

Get logs from OpenShift resources like pods, deployments, builds, etc. with advanced filtering and streaming options

NameTypeReqDescription
allContainersbooleanGet logs from all containers in the pod
containerstringContainer name (for pods with multiple containers)
contextstringOpenShift context to use (optional)
followbooleanFollow logs output (stream live logs)
limitBytesnumberMaximum bytes to return
maxLogRequestsnumberMaximum number of concurrent log requests when using selectors
namestringyesName of the resource
namespacestringOpenShift namespace/project
previousbooleanShow logs from previous terminated container
resourceTypestringType of resource to get logs from
selectorstringLabel selector to filter pods
sincestringShow logs since relative time (e.g. 5s, 2m, 3h) or absolute time
sinceTimestringShow logs since absolute timestamp (RFC3339)
tailnumberNumber of lines to show from end of logs (-1 for all)
timestampsbooleanInclude timestamps in log output

No output schema declared.

No examples provided.

oc_new_app ~271

Create a new application from a GitHub repository using S2I build and expose it with an edge-terminated route

NameTypeReqDescription
appNamestringName for the application (if not specified, derives from repo name)
builderImagestringBuilder image for S2I build (e.g., "nodejs:18-ubi8", "python:3.9-ubi8")
contextstringOpenShift context to use (optional)
contextDirstringContext directory within the Git repository
createNamespacebooleanCreate namespace if it does not exist
envarrayEnvironment variables in KEY=VALUE format
exposeRoutebooleanCreate an edge-terminated route to expose the application
gitRefstringGit reference (branch, tag, or commit) to build from (default: main/master)
gitRepostringyesGitHub repository URL for the source code
labelsarrayLabels in KEY=VALUE format
namespacestringTarget namespace for the application
routeHostnamestringCustom hostname for the route (if not specified, uses default)
strategystringBuild strategy: source (S2I) or docker

No output schema declared.

No examples provided.

oc_patch ~233

Patch OpenShift resources with strategic merge, JSON merge, or JSON patch operations

NameTypeReqDescription
contextstringOpenShift context to use (optional)
dryRunbooleanPerform a dry run without making actual changes
fieldManagerstringField manager name for server-side apply tracking
forcebooleanForce the patch operation, ignoring conflicts
namestringyesName of the resource to patch
namespacestringNamespace/project for the resource (not required for cluster-scoped resources)
patchstringyesPatch content as JSON string or YAML. For strategic merge patch (default), provide the fields to update. For JSON patch, use RFC 6902 format.
patchTypestringType of patch operation
recordHistorybooleanRecord the patch operation in the resource annotation for rollback purposes
resourceTypestringyesType of resource to patch (pod, deployment, service, route, configmap, secret, etc.)
subresourcestringSubresource to patch (e.g., status, scale)

No output schema declared.

No examples provided.

oc_scale ~109

Scale the number of pods in a deployment, deploymentconfig, replicaset, or statefulset to the specified number of replicas

NameTypeReqDescription
contextstringOpenShift context to use (optional)
namestringyesName of the resource to scale
namespacestringOpenShift namespace/project
replicasnumberyesNumber of replicas to scale to
resourceTypestringResource type to scale (deployment, deploymentconfig, replicaset, statefulset)

No output schema declared.

No examples provided.

Common questions

What is the OpenShift MCP Server server?

OpenShift MCP Server is listed in the public MCP registry as io.github.sanjaypsachdev/mcp-server-openshift. OpenShift/Kubernetes cluster management via the oc CLI for MCP clients. This page covers its npm package (mcp-server-openshift).

Is the OpenShift MCP Server server safe to use?

OpenShift MCP Server scores 72 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the OpenShift MCP Server server expose?

OpenShift MCP Server exposes 14 tools: oc_get, oc_create, oc_install_operator, oc_new_app, oc_scale, and 9 more. Their descriptions and schemas cost roughly 2,982 tokens of context every time the server is loaded.

Is the OpenShift MCP Server server still maintained?

OpenShift MCP Server is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the OpenShift MCP Server server under?

OpenShift MCP Server declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.