Kubernetes Resources Reference
About
Help AI agents write accurate, up-to-date Kubernetes manifests by giving them the official Kubernetes API reference, so they can look up kinds, fields, and nested types with current specs across the latest and three previous Kubernetes versions.
Details
- Author
- kubernetools
- Downloads
- 253
- Categories
- Cloud Service, Other, Infrastructure, Knowledge Base, Developer Tools
Jump to
- Free hosted service, no sign-up or API key required.
- Queries official Kubernetes API definitions.
- Supports multiple Kubernetes versions per URL parameter.
- Browse or search for Kubernetes resource kinds.
- Look up every field of a specific resource.
- Drill into nested types mentioned in other resources.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Kubernetes Resources ReferenceCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Connect your MCP‑compatible client by adding the server URL (e.g., https://mcp.kubernetools.com/?version=v1.36) to the client’s mcpServers configuration in JSON. No sign-up or API key is required. The ?version= parameter lets you specify which Kubernetes release to query; omit it to use the latest version.
list_resources
Lightweight discovery — one entry per Kubernetes resource. Use this first to discover available kinds.
get_resource
Full resource detail — fields, spec, status, and list fields — enough to write a manifest in one call.
get_type
Drill into a single complex type referenced by get_resource (via type_ref fields).
compare_resource_versions
Compare a resource kind between two of its API versions within Kubernetes v1.35 (e.g. v1beta1 vs v1): fields added, removed, or changed.
diff_previous_version
Changes introduced in Kubernetes v1.35 (this instance's version) since v1.34: resources and types added, removed, or structurally changed.
diff_next_version
Changes the next Kubernetes version (v1.36) introduces relative to v1.35 (this instance's version): resources and types added, removed, or structurally changed.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"kubernetes resources reference": {
"kubernetools-1.35": {
"type": "http",
"url": "https://mcp.kubernetools.com/?version=v1.35"
},
"kubernetools-1.36": {
"type": "http",
"url": "https://mcp.kubernetools.com/?version=v1.36"
}
}
}
}
McpServers
{
"kubernetools-1.35": {
"type": "http",
"url": "https://mcp.kubernetools.com/?version=v1.35"
},
"kubernetools-1.36": {
"type": "http",
"url": "https://mcp.kubernetools.com/?version=v1.36"
}
}
Help AI agents write accurate, up-to-date Kubernetes manifests by giving them the official Kubernetes API reference, so they can look up kinds, fields, and nested types with current specs across the latest and three previous Kubernetes versions
- Discover available Kubernetes resource kinds— ask the AI to calllist_resourcesto see all resource types, optionally filtered by API group or version.
- Get the full schema for a resource— useget_resourceto retrieve every field, spec, and status detail needed to write a manifest for a given kind.
- Drill into nested type definitions— when a field references a complex type, callget_typeby name to expand its structure and sub-fields.
- Target a specific Kubernetes version— connect with aversionquery parameter to work against the API schema of a particular release like v1.36.
Container image for thekubernetoolsMCP server.
Registry:ghcr.io/kubernetools/mcp-server
No authentication required; all connections are rate-limited per source IP at the free-tier limit.
podman run -d \ -p 3000:3000 \ -e K8S_VERSIONS=v1.33 \ ghcr.io/kubernetools/mcp-server:latest
# 1. Create a key store file echo '[{"key":"mykey","tier":"free"}]' > keys.json # 2. Start the server podman run -d \ -p 3000:3000 \ -v "$(pwd)/keys.json:/keys.json:ro" \ -e K8S_VERSIONS=v1.33,v1.34,v1.35,v1.36 \ -e KEY_STORE_PATH=/keys.json \ ghcr.io/kubernetools/mcp-server:latest
The key store is a flat JSON array loaded once at startup:
[ { "key": "free-key-abc", "tier": "free" }, { "key": "paid-key-xyz", "tier": "paid" } ]
Every request must include the key in theAuthorizationheader:
Requests without a valid key receive401 Unauthorized.
WhenKEY_STORE_PATHis not set, the server runs without authentication. All connections are accepted and rate-limited per source IP at the free-tier limit. Convenient for local use; do not expose publicly.
Requests that exceed the limit receive429 Too Many Requests. Limits are tracked per API key, not per IP.
The server implements theMCP Streamable HTTP transport. The endpoint is:
http://<host>:<port>/[?version=<k8s-version>]
Theversionquery parameter selects which Kubernetes version to use for the session. If omitted, the first loaded version is used. An unknown version returns400 Bad Request.
Add the following toclaude_desktop_config.json:
{ "mcpServers": { "kubernetools": { "url": "http://localhost:3000/?version=v1.36", "headers": { "Authorization": "Bearer mykey" } } } }
Lightweight discovery — returns one entry per resource, sorted by(group, kind, api_version). Use this first to find kind names.
Optional filters:group(e.g."apps","core"),api_version(e.g."v1").
Full resource detail — fields, spec, status, and list fields — enough to write a manifest in one call. Required:kind. Optional:group,api_version(defaults to most recent).
Fields with a non-nulltype_refand emptysub_fieldsshould be drilled into withget_type.
Drill into a single composite type referenced viatype_refinget_resourceoutput. Required:type_name(e.g."Container","PodFailurePolicy").
list_resources → discover kind names and groups └─ get_resource(kind="Deployment") → see all top-level fields + spec/status └─ get_type(type_name="...") → drill into any complex type_ref
- Returns503 Service Unavailable(body:loading) while Kubernetes API docs are loading.
- Returns200 OK(body:ok) once the server is ready.
This endpoint bypasses authentication and rate limiting.
Use it for startup, readiness, and liveness probes:
startupProbe: httpGet: path: /healthz port: 3000 failureThreshold: 30 # allow up to 5 min for version loading periodSeconds: 10 readinessProbe: httpGet: path: /healthz port: 3000 livenessProbe: httpGet: path: /healthz port: 3000 initialDelaySeconds: 10
MCP-level errors (unknown tool name, missing required argument, kind not found) are returned as MCP error content inside a normal200response.
podman run -d \ -p 3000:3000 \ -v "$(pwd)/keys.json:/keys.json:ro" \ -e K8S_VERSIONS=v1.33,v1.34,v1.35,v1.36 \ -e GITHUB_TOKEN=ghp_... \ -e KEY_STORE_PATH=/keys.json \ ghcr.io/kubernetools/mcp-server:latest
podman run -d \ -p 3000:3000 \ -v "$(pwd)/keys.json:/keys.json:ro" \ -e K8S_VERSIONS=v1.36 \ -e KEY_STORE_PATH=/keys.json \ -e ALLOWED_HOSTS=mcp.example.com,mcp.example.com:443 \ -e BROWSER_REDIRECT_URL=https://example.com/docs \ ghcr.io/kubernetools/mcp-server:latest
podman run -d \ -p 3000:3000 \ -e K8S_VERSIONS=v1.33 \ -e RUST_LOG=debug \ ghcr.io/kubernetools/mcp-server:latest
podman run -d \ -p 3000:3000 \ -e K8S_VERSIONS=v1.33 \ ghcr.io/kubernetools/mcp-server:0.1.0
Search and retrieve detailed information, including READMEs, for Helm charts on Artifact Hub.
Expose the entire ArgoCD API to LLMs via MCP using just 2 auto-generated tools powered by the OpenAPI spec.
An MCP server for managing Kubernetes clusters, configured via an external JSON file.
A comprehensive Model Context Protocol (MCP) server for the Cloudability API, providing advanced cost management, Kubernetes container analytics, and budget forecasting capabilities.
A server for managing Giant Swarm App Platform deployments using Kubernetes credentials.
Read-only MCP server for AI-powered Kubernetes debugging with support of code execution
Tilt MCP is a Model Context Protocol server that integrates with Tilt to provide programmatic access to Tilt resources, logs, and management operations for Kubernetes development environments
Operate a k3s / Kubernetes cluster from your AI agent — health, logs, and guarded restart/scale/delete; safe by default with a read-only switch and namespace allowlist.
MCP server that generates production-grade engineering standards (SOLID, testing, architecture, CI/CD) for AI coding assistants
Run and interpret Kubernetes commands interactively with a provided kubeconfig.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.




