Kubernetes MCP Server
MCP server that lets agents run kubectl and Helm operations to inspect and manage Kubernetes clusters.
Kubernetes MCP Server
This Model Context Protocol server gives AI agents a controlled interface to Kubernetes clusters, wrapping kubectl and Helm so an assistant can inspect workloads, debug failures, and apply changes without hand-copying commands.
Key features
- Core
kubectlverbs: get, describe, list, apply, delete across pods, deployments, services, and more - Log retrieval and pod exec for hands-on debugging of failing workloads
- Helm install, upgrade, and uninstall for managing packaged releases
- Port-forwarding and scaling operations driven from natural-language requests
- Uses your existing kubeconfig and context, respecting current RBAC permissions
- Optional non-destructive mode that blocks delete/apply for safer read-only exploration
It turns cluster operations into agent-operable tools, letting an assistant triage an incident — read events, tail logs, scale a deployment — through one consistent MCP surface instead of a shell.
Curated mirror of the open-source mcp-server-kubernetes (MIT). Get it from the source.
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
The same gate an agent runs before installing (POST /api/v1/trust/kubernetes-mcp-server/check). Click a policy:
Consume Kubernetes MCP Server programmatically. Authenticate with an API key or session — see Authorize an agent.
# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/kubernetes-mcp-server
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/kubernetes-mcp-server/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add kubernetes-mcp-server
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/kubernetes-mcp-server/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "kubernetes-mcp-server" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.