Skip to content
MCP server

KubeDrive

Read-only Kubernetes cluster access for AI agents, served by the KubeDrive desktop app

Runs locallyStatus and history
Pricing
Freemium
Runs
Locally
Version
0.6.8
Listing updated
3 days ago

About KubeDrive

KubeDrive is a freemium MCP server for developer tools. It runs locally on your machine and is started by your AI client.

KubeDrive answers an agent's questions from the connections the desktop app already holds, so the agent never receives a kubeconfig or cluster token. The server listens on localhost only and stays off until you switch it on from the AI Agents window.

You choose which clusters are shared, and each one can carry its own rules: limit reads to listed namespaces, hide Secrets entirely, allow or block individual write actions, or make agent changes land as proposals. Every change waits for your Allow in a window unless a rule says otherwise. A shared cluster is tied to the API server it pointed at when you ticked it.

Setup snippets are provided for Claude Code, Codex, Cursor and Claude Desktop, which uses a small stdio bridge.

Install

Run in a terminal

claude mcp add kubedrive --env KUBEDRIVE_MCP_TOKEN='<KUBEDRIVE_MCP_TOKEN>' -- npx -y https://github.com/kubedrive/kubedrive/releases/download/v0.6.8/kubedrive-0.6.8.mcpb

Add to claude_desktop_config.json

{
  "mcpServers": {
    "kubedrive": {
      "command": "npx",
      "args": [
        "-y",
        "https://github.com/kubedrive/kubedrive/releases/download/v0.6.8/kubedrive-0.6.8.mcpb"
      ],
      "env": {
        "KUBEDRIVE_MCP_TOKEN": "<KUBEDRIVE_MCP_TOKEN>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "kubedrive": {
      "command": "npx",
      "args": [
        "-y",
        "https://github.com/kubedrive/kubedrive/releases/download/v0.6.8/kubedrive-0.6.8.mcpb"
      ],
      "env": {
        "KUBEDRIVE_MCP_TOKEN": "<KUBEDRIVE_MCP_TOKEN>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "kubedrive": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "https://github.com/kubedrive/kubedrive/releases/download/v0.6.8/kubedrive-0.6.8.mcpb"
      ],
      "env": {
        "KUBEDRIVE_MCP_TOKEN": "<KUBEDRIVE_MCP_TOKEN>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "kubedrive": {
      "command": "npx",
      "args": [
        "-y",
        "https://github.com/kubedrive/kubedrive/releases/download/v0.6.8/kubedrive-0.6.8.mcpb"
      ],
      "env": {
        "KUBEDRIVE_MCP_TOKEN": "<KUBEDRIVE_MCP_TOKEN>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "kubedrive": {
      "command": "npx",
      "args": [
        "-y",
        "https://github.com/kubedrive/kubedrive/releases/download/v0.6.8/kubedrive-0.6.8.mcpb"
      ],
      "env": {
        "KUBEDRIVE_MCP_TOKEN": "<KUBEDRIVE_MCP_TOKEN>"
      }
    }
  }
}

Configuration

  • KUBEDRIVE_MCP_TOKENThe client token from KubeDrive → AI Agents, after the server is turned on; starts with kd_Required
  • KUBEDRIVE_MCP_URLKubeDrive's MCP endpoint, only if its port was changed

Tools this server provides (2)

Taken from the project documentation; the running server may differ.

cluster_problems
Whole-cluster problem scan
upgrade_check
Check readiness for a cluster upgrade

What it does

No kubeconfig for the agent
The agent asks KubeDrive, which reuses your own kubeconfig, SSO sessions and RBAC.
Per-cluster rules
Restrict namespaces, hide Secrets, and toggle each write action per cluster.
Approval for changes
Agent changes wait for your Allow, with delete, exec and drain off by default.
Activity indicator
A title-bar icon shows server state and counts each agent call.
Cluster diagnosis tools
Whole-cluster tools such as cluster_problems and upgrade_check are available when reads are not namespace-limited.

Good for

  • Ask why a deployment in staging is not ready
  • Find which pods restarted most in the last hour
  • Check a cluster before an upgrade
  • Let an agent propose a change for you to review

Pricing

Freemium, from $8 a month

Free for one agent and read-only; Pro $8/month or $79/year

Prices change. Check kubedrive.com before you buy.

KubeDrive FAQ

Does the agent get my cluster credentials?

No. KubeDrive uses its own connections and the agent only gets answers.

Is it free?

Reading is free for one agent at a time. A second client and agent-made changes need Pro, at $8 a month or $79 a year.

Can I limit what an agent sees?

Yes, by namespace, and you can hide Secrets entirely for a cluster.

Is the server reachable from the network?

It runs at 127.0.0.1 on port 47011 on your computer only.

Is KubeDrive free?

KubeDrive has a free plan, with paid plans for more usage or features. Paid plans start at $8 a month.

How do I add KubeDrive to Claude Code?

Run this command in your terminal: claude mcp add kubedrive --env KUBEDRIVE_MCP_TOKEN='<KUBEDRIVE_MCP_TOKEN>' -- npx -y https://github.com/kubedrive/kubedrive/releases/download/v0.6.8/kubedrive-0.6.8.mcpb

What are the best alternatives to KubeDrive?

The closest alternatives to KubeDrive are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to KubeDrive

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools