Enterprise DNA Enterprise DNA
M MCP Servers Developer low

garlicKim21/ratatosk-mcp

by Various

MCP server for Ratatosk — CNCF release intelligence facts for AI agents. checkstack compares your running versions locally; only project slugs leave your cluster.

MCP

garlicKim21/ratatosk-mcp

Added 21 Sept 2026

#ai-agents #cloud-native #cncf #devops #golang #kubernetes #mcp #mcp-server

Overview

MCP server for Ratatosk that exposes CNCF release intelligence facts to AI agents. It includes checkstack, which compares running versions locally and only sends project slugs outside the cluster. Written in Go.

Best for

Best for
Developers building AI agents that need CNCF release facts without exposing cluster details

Use cases

  • Compare local running versions against CNCF release data
  • Provide release intelligence to AI agents via MCP
  • Audit cluster versions with minimal data exfiltration

How to use

Install

docker run -i --rm ghcr.io/garlickim21/ratatosk-mcp:0.9.0

Tools exposed

  • check_stack
  • list_changes
  • changes_by_entity
  • get_matter
  • get_release
  • list_releases
  • list_projects

Tested with

Claude Desktop, Claude Code, kagent

Notes

MCP server for Ratatosk that exposes CNCF release intelligence facts to AI agents. It includes checkstack, which compares running versions locally and only sends project slugs outside the cluster. Written in Go.

2 stars on GitHub. Last updated 2026-09-04. Licensed Apache-2.0.

Use cases

  • Compare local running versions against CNCF release data
  • Provide release intelligence to AI agents via MCP
  • Audit cluster versions with minimal data exfiltration

Pros

  • Lightweight Go implementation
  • Privacy-focused design, only project slugs leave the cluster
  • Simple MCP integration for AI agents

Cons

  • Very early stage with only 2 stars
  • Limited adoption and community
  • Requires Ratatosk as a dependency

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Lightweight Go implementation
  • Privacy-focused design, only project slugs leave the cluster
  • Simple MCP integration for AI agents

Cons

  • Very early stage with only 2 stars
  • Limited adoption and community
  • Requires Ratatosk as a dependency
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks