kubectl-mcp-server
Published in CNCF Landscape: A MCP server for Kubernetes.
No outside reports on file
This tool gives an AI direct power over your Kubernetes cluster, so only use it if you trust the AI system, run it with minimal permissions, and keep close watch on what it does.
Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionRuns shell or system commandsREVIEW
- Network reachConnects to outside service APINOTED
- CredentialsRequires API key or tokenREVIEW
- Package sourceGitHub (rohitg00/kubectl-mcp-server)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/rohitg00/kubectl-mcp-server ↗
Everything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-23.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About Kubectl MCP Server
This is a Model Context Protocol (MCP) server that lets AI assistants like Claude run Kubernetes commands. It acts as a bridge so an AI can interact with your Kubernetes clusters to check status, manage resources, and perform operations.
Who it’s for
Developers and DevOps teams who want to give AI assistants the ability to help manage Kubernetes clusters. It's for people who trust an AI tool with access to their Kubernetes environment.
Alternatives
- Kubernetes native tools: kubectl plugins and dashboards for direct cluster management
- Cloud provider integrations: Native AI integrations from AWS, Google Cloud, or Azure
- Helm MCP servers: Alternative MCP servers focused on Helm package management
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README on GitHub for installation and configuration instructions. The setup likely involves adding the server to your MCP configuration file with appropriate credentials and cluster details.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 965
- Listing last refreshed
- 2026-10-29
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- Kubernetes cluster access: The server can run any kubectl command your credentials allow, potentially creating, deleting, or modifying workloads and data
- Credential exposure: Kubernetes credentials (kubeconfig files, tokens) needed by this server could be leaked if misconfigured or if the AI assistant is compromised
- Prompt injection attacks: An attacker could embed hidden commands in Kubernetes resource descriptions or logs that trick the AI into running dangerous operations
- Unintended modifications: An AI might misunderstand requests and make unplanned changes to your cluster, deleting pods or altering configurations
- Audit trail gaps: The AI's actions through this server might not appear clearly in Kubernetes audit logs as human-initiated, making troubleshooting harder
How to lower the risk
Least-privilege permissions
- Create a Kubernetes service account with only the specific permissions needed
- Use RBAC (role-based access control) to limit what kubectl commands work
Network isolation
- Run the MCP server on a private network, not exposed to the internet
- Restrict which AI systems can access this server
Monitoring
- Enable Kubernetes audit logging to track all operations
- Review logs regularly for unexpected or suspicious commands
Red flags to watch for
- Requests to create admin users or escalate permissions
- Commands targeting secrets or sensitive namespaces
- Unusual cluster modifications you didn't request
Questions
How do I install Kubectl MCP Server?
Kubectl MCP Server does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/rohitg00/kubectl-mcp-server.
Are there security reports about Kubectl MCP Server?
No reports found for this package in our research (last checked 2026-10-30). Kubectl MCP Server currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include kubernetes cluster access, credential exposure, prompt injection attacks.
Is Kubectl MCP Server actively maintained?
Kubectl MCP Server has 965 GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/rohitg00/kubectl-mcp-server before pinning it in production.
What are alternatives to Kubectl MCP Server?
Notable alternatives to Kubectl MCP Server include Kubernetes native tools (kubectl plugins and dashboards for direct cluster management), Cloud provider integrations (Native AI integrations from AWS, Google Cloud, or Azure), Helm MCP servers (Alternative MCP servers focused on Helm package management). You can also compare Kubectl MCP Server side by side with other MCP servers in the Related tools section on this page.
Key facts
- Type
- App connector
- Publisher
- rohitg00
- Source code
- github.com/rohitg00/kubectl-mcp-server
- Est. context load
- ~700 tokens / turn (~4 tool schemas, 0.35% of 200k context)
- Popularity
- 965 GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-23
Community
Discussions for Kubectl MCP Server
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude