k8s-mcp-server

Provides a Go-based Model Context Protocol (MCP) server that exposes Kubernetes resources as MCP tools (e.g., Pod/Deployment/Service/etc.) and also offers a generic custom-resource tool for CRDs. Operations are executed against a Kubernetes cluster using a provided kubeconfig.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ Infrastructure kubernetes mcp ai-agents devtools automation rbac golang infrastructure
⚙ Agent Friendliness
49
/ 100
Can an agent use this?
🔒 Security
41
/ 100
Is it safe for agents?
⚡ Reliability
22
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
55
Error Messages
0
Auth Simplicity
70
Rate Limits
10

🔒 Security

TLS Enforcement
40
Auth Strength
55
Scope Granularity
45
Dep. Hygiene
30
Secret Handling
30

Security depends on the kubeconfig’s Kubernetes RBAC; the README states operations are restricted by RBAC. However, the README does not specify transport security, secret-handling/logging behavior, audit logging, or additional agent-level safeguards. The custom tool uses a gRPC backend URL, increasing the need to trust/configure that endpoint securely.

⚡ Reliability

Uptime/SLA
0
Version Stability
40
Breaking Changes
20
Error Recovery
30
AF Security Reliability

Best When

You have a properly scoped kubeconfig (RBAC-limited), and you run the MCP server in a controlled environment (e.g., local/sidecar) where the agent’s allowed actions map cleanly to Kubernetes RBAC.

Avoid When

You cannot constrain permissions (RBAC) or you are unable to limit what the agent can do (e.g., broad cluster-admin kubeconfig).

Use Cases

  • Let an AI agent inspect Kubernetes state (Get/List/Logs) via MCP tools
  • Enable controlled Kubernetes CRUD workflows (create/update/delete) driven by agent actions
  • Support automation of common workloads (deployments/services/namespaces) from natural-language or tool calls
  • Handle Kubernetes custom resources (CRDs) via a generic custom tool

Not For

  • Untrusted or unauthenticated agent environments where kubeconfig credentials could be abused
  • Workloads requiring fine-grained auditability beyond Kubernetes RBAC
  • High-assurance production control without additional guardrails (approvals, policy enforcement)

Interface

REST API
No
GraphQL
No
gRPC
Yes
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Kubeconfig-based access to Kubernetes API
OAuth: No Scopes: No

Authentication is implicitly via the provided kubeconfig; the effective authorization is determined by Kubernetes RBAC permissions on that kubeconfig.

Pricing

Free tier: No
Requires CC: No

Open-source installation via Go; no pricing information provided in README.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • CRUD tool calls can be destructive (update/delete); ensure the kubeconfig/RBAC is tightly scoped before enabling the server
  • List/Get operations may still require broad permissions depending on resource type
  • Custom resource tool relies on a separate gRPC backend URL (customURL), which adds another moving part to configure correctly

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for k8s-mcp-server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered