io.github.ai-4-devops/devops-practices
AI-powered DevOps knowledge base with practices, templates, and automation tools
Ask AI about io.github.ai-4-devops/devops-practices
Powered by Claude Β· Grounded in docs
I know everything about io.github.ai-4-devops/devops-practices. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
DevOps Practices - MCP Server
mcp-name: io.github.ai-4-devops/devops-practices
Purpose: Productivity framework for DevOps engineers using AI assistance (Claude Code) while working on PoCs.
Type: Model Context Protocol (MCP) Server for Claude Code
Version: 1.4.0
Status: π Officially Published in the MCP Registry (Published: February 18, 2026)
Published Versions:
- π¦ PyPI: v1.4.0 β Git tag v1.4.0 (
34ca572) - π MCP Registry: v1.4.0 β Git tag v1.4.0 (
34ca572) - π Latest Development: main branch (may include unreleased features)
Who is this for? DevOps engineers using Claude Code (VS Code plugin) for PoC development. What it does: Provides structure (TRACKER, ISSUES, docs, SoPs) so you can focus on building without worrying about documentation overhead. What it's NOT: Not a DevOps tutorial - it's a productivity framework for AI-assisted development.
Why This MCP Server?
Solves the CLAUDE.md Bloat Problem
Tired of maintaining massive CLAUDE.md files (1000+ lines) across multiple projects? This MCP centralizes reusable DevOps instructions for engineers working on multiple PoCs, eliminating repeated instructions across projects and folders.
The Problem:
- β Large CLAUDE.md files eat up context window
- β Same practices duplicated across every project
- β Reinventing TRACKER.md, ISSUES.md, docs, SoPs for every PoC
- β Inconsistent standards across projects
- β Context wasted on instructions instead of actual work
The Solution:
- β Pre-built structure - Templates for TRACKER, ISSUES, docs, SoPs
- β Focus on work - Not on "how should I document this?"
- β Consistency - Same standards across all your PoCs
- β Team alignment - Same patterns enable seamless collaboration and easy handovers across sessions, systems, and team members
- β Faster startup - Copy template, start working
- β Context saved - No bloated CLAUDE.md files
What you get (structure, not knowledge):
- π TRACKER.md template - Start tracking immediately, don't design tracking
- π ISSUES.md system - Start logging issues, don't setup Jira
- π Documentation standards - Start writing docs, don't debate structure
- π Runbook templates - Start documenting ops, don't create SoP formats
- π Session continuity - Start handoffs, don't design handoff protocols
When searching "devops" in the MCP Registry (as of February 2026), this is the only result. While other MCPs focus on:
- π§ Development tools (code generation, testing, debugging)
- π Data analysis (databases, APIs, analytics)
- π¨ Content creation (writing, design, media)
This MCP provides:
- ποΈ Configuration structure - How to organize configs per environment, generate new env configs from completed ones, create and validate SoPs
- π Documentation patterns - TRACKER, ISSUES, docs, runbook templates ready to copy
- π Operations templates - Session handoff, runbook formats, documentation standards
- π― Structured guidance - GG-SS organized practices for quick discovery
What makes it different:
- Prescriptive, not generative - Provides proven practices, not generated code
- Infrastructure-first - Built for ops teams, not developers
- Reusable patterns - Templates and standards across all your projects
- AI-native design - Organized for Claude to query and apply contextually
- R&D optimized - Accelerates proof-of-concept development and experimentation
Perfect for: DevOps engineers using Claude Code (VS Code plugin) to build PoCs and conduct R&D with AI assistance.
How It Works
No server management required:
- β Auto-start: Spawns when Claude Code/Desktop starts
- β Background: Runs silently while you work
- β On-demand: Claude queries practices as needed
- β Auto-stop: Shuts down when Claude closes
- β Fallback: Access practices via GitHub/local if MCP unavailable (see Troubleshooting)
Configuration Options:
You can configure the MCP server globally (all projects) or per-project:
Option 1: Global Configuration (~/.claude.json)
{
"mcpServers": {
"devops-practices": {
"command": "python3",
"args": ["-u", "~/.mcp-servers/devops-practices/mcp-server.py"],
"env": {"PYTHONUNBUFFERED": "1"}
}
}
}
Option 2: Project-Level Configuration (.mcp.json in project root)
{
"mcpServers": {
"devops-practices": {
"command": "python3",
"args": ["-u", "~/.mcp-servers/devops-practices/mcp-server.py"],
"env": {"PYTHONUNBUFFERED": "1"}
}
}
}
Setup Steps:
- Install the MCP server (see Installation section below)
- Add configuration to
~/.claude.json(global) or.mcp.json(per-project) - Restart Claude Code/Desktop
- MCP server runs automatically - no manual startup needed
Note: The -u flag and PYTHONUNBUFFERED ensure real-time logging for debugging.
What This Provides
This MCP server provides shared DevOps practices that are common across infrastructure projects:
Available Practices (11)
Organized using GG-SS prefix pattern (Group-Sequence) for better discoverability:
Naming Pattern: GG-SS-practice-name
- GG = Group ID (01-04) - Functional category
- SS = Sequence ID (01-03) - Order within group
- Example:
03-02-air-gapped-workflow= Group 03, Sequence 02
Group Legend:
- 01 = Workflow & Processes (how to work effectively)
- 02 = Version Control & Project Management (git, issues)
- 03 = Infrastructure & Configuration (K8s, deployments, config)
- 04 = Documentation Standards (docs, READMEs, runbooks)
Group 01: Workflow & Processes
- 01-01-session-continuity - State tracking, handoff protocols, CURRENT-STATE.md
- 01-02-task-tracking - TRACKER.md, CURRENT-STATE.md, PENDING-CHANGES.md
- 01-03-efficiency-guidelines - When to script vs copy-paste, batching commands
Group 02: Version Control & Project Management
- 02-01-git-practices - Using
git mv, commit conventions, backup protocols, GitLab Flow - 02-02-issue-tracking π - In-repository Jira-like issue tracking system (Advanced)
Group 03: Infrastructure & Configuration
- 03-01-configuration-management β - Config organization, placeholders, environment isolation
- 03-02-air-gapped-workflow - Working across laptop, CloudShell, bastion, and EKS
- 03-03-standard-workflow - Common operational patterns and workflows
Group 04: Documentation Standards
- 04-01-documentation-standards - HOW/WHAT/WHY structure, naming conventions
- 04-02-readme-maintenance β - Directory documentation standards and best practices
- 04-03-runbook-documentation β - Mandatory session log standards and requirements
Available Templates (7)
- TRACKER.md - Task tracking template (milestones)
- CURRENT-STATE.md - Session handoff template
- CLAUDE.md - Simplified project instructions template
- RUNBOOK.md β - Session log template with all required sections
- ISSUE.md π - Individual issue template (Advanced)
- ISSUES.md π - Issue index template with stats dashboard (Advanced)
- issues/README.md π - How to use the issue system (Advanced)
Architecture
devops-practices-mcp/
βββ README.md # This file
βββ mcp-server.py # MCP server implementation
βββ requirements.txt # Python dependencies
βββ .github/workflows/ci.yml # GitHub Actions pipeline
βββ health-check.sh # Health validation script
βββ practices/ # Shared practice documents (11 files, GG-SS organized)
β βββ 01-01-session-continuity.md
β βββ 01-02-task-tracking.md
β βββ 01-03-efficiency-guidelines.md
β βββ 02-01-git-practices.md
β βββ 02-02-issue-tracking.md # π Advanced: In-repo issue tracking
β βββ 03-01-configuration-management.md
β βββ 03-02-air-gapped-workflow.md
β βββ 03-03-standard-workflow.md
β βββ 04-01-documentation-standards.md
β βββ 04-02-readme-maintenance.md
β βββ 04-03-runbook-documentation.md
βββ templates/ # File templates (7 files)
β βββ TRACKER-template.md
β βββ CURRENT-STATE-template.md
β βββ CLAUDE-template.md
β βββ RUNBOOK-template.md
β βββ ISSUE-TEMPLATE.md # π Individual issue template
β βββ ISSUES.md # π Issue index with dashboard
β βββ issues-README.md # π Issue system guide
βββ tools/ # Automation tools π
β βββ issue-manager.sh # CLI for managing issues
βββ config/ # MCP configuration
βββ mcp-config.json # Server configuration
MCP Tools
The MCP server provides 5 tools for Claude to query practices and templates:
| Tool | Description | Example |
|---|---|---|
list_practices | List all available practices | Returns list of 10 practices |
get_practice | Get practice content by name | get_practice("01-02-task-tracking") |
list_templates | List all available templates | Returns list of 4 templates |
get_template | Get template content by name | get_template("TRACKER-template") |
render_template | Render template with variable substitution | render_template("TRACKER-template", {"PROJECT_NAME": "my-project"}) |
Template Variable Substitution
Templates support ${VARIABLE} placeholders that are automatically substituted:
Auto-provided variables:
${DATE}- Current date (YYYY-MM-DD format)${TIMESTAMP}- UTC timestamp (YYYYMMDDTHHMMz format)${USER}- Current system user${YEAR}- Current year
Custom variables: Pass any additional variables when rendering:
render_template("RUNBOOK-template", {
"SESSION_NUMBER": "1",
"TITLE": "Kafka Deployment",
"CLUSTER_NAME": "example-eks-uat",
"OBJECTIVE_DESCRIPTION": "Deploy Kafka cluster to UAT"
})
All ${...} placeholders in the template are replaced with provided values.
CI/CD Pipeline
This repository includes a GitHub Actions pipeline (.github/workflows/ci.yml) that automatically validates changes:
Pipeline Jobs
On every merge request and commit to main/develop:
- health-check - Runs the comprehensive health check script
- python-validation - Validates Python syntax and dependencies
- practice-validation - Ensures all practice files exist
- template-validation - Ensures templates contain variable placeholders
- link-checker - Checks documentation cross-references
Benefits
- β Prevents breaking changes from reaching main branch
- β Catches missing files or syntax errors automatically
- β Ensures consistent quality standards
- β No manual validation needed
Pipeline Status
Check pipeline status in GitHub:
- Green checkmark β - All checks passed, safe to merge
- Red X β - Checks failed, review errors before merging
Documentation
Quick Reference
- PRACTICE-INDEX.md - Quick lookup guide for which practice to use when
- Organized by task type (deploying, documenting, troubleshooting, etc.)
- Common scenarios with recommended practices
- Practice dependencies and relationships
Migration Guide
- MIGRATION-GUIDE.md - Roll out MCP to existing projects
- Step-by-step migration from monolithic CLAUDE.md
- Configuration setup for Claude Desktop/Code
- Testing and validation procedures
- Rollback plan if needed
Version History
- CHANGELOG.md - Complete version history and upgrade guides
- Version 1.0.0 (2026-02-13): 10 practices, 4 templates, health check tool
- Version 0.1.0 (2026-02-13): Initial release
Health Check
- health-check.sh - Validate MCP server before deployment
- 14 comprehensive checks (directory structure, files, Python environment, loading tests)
- Colored output with pass/fail counts
- Exit codes: 0 (healthy), 1 (unhealthy)
Usage:
cd devops-practices-mcp
bash health-check.sh
How Projects Use This
Project CLAUDE.md Structure
Each project has a simplified CLAUDE.md:
# Claude AI Assistant - [Project Name]
## MCP Service Integration
**Shared Practices**: `devops-practices` MCP server
Claude has access to shared DevOps practices via MCP:
- Air-gapped workflow
- Documentation standards
- Session continuity protocols
- Task tracking guidelines
- Git best practices
- Efficiency guidelines
β οΈ Fallback: If MCP unavailable, see Appendix or GitHub practices
## Project-Specific: [Project Details]
[Only project-specific instructions here]
## Appendix: Critical Practices (Fallback)
[Emergency practice summaries if MCP down - see CLAUDE-template.md]
Benefits
- DRY: Shared practices written once, used everywhere
- Consistency: All projects follow same standards
- Maintainability: Update once, all projects benefit
- Discoverability: Claude can query practices when needed
- Resilient: Fallback to GitHub/local/appendix if MCP unavailable
Template: See CLAUDE-template.md for full structure including fallback appendix
Installation & Setup
π§ Manual Installation (Most Stable - Recommended for Development)
Best for: Developers, contributors, or anyone who wants full control
1. Clone Repository
# Clone to recommended location
git clone https://github.com/ai-4-devops/devops-practices.git ~/.mcp-servers/devops-practices
cd ~/.mcp-servers/devops-practices
2. Install Dependencies
# Using uv (10-100x faster)
curl -LsSf https://astral.sh/uv/install.sh | sh
uv pip install -r requirements.txt
# Or using traditional pip
pip install -r requirements.txt
3. Configure MCP Server
Edit ~/.claude/config.json:
{
"mcpServers": {
"devops-practices": {
"command": "python3",
"args": ["-u", "~/.mcp-servers/devops-practices/mcp-server.py"],
"env": {"PYTHONUNBUFFERED": "1"}
}
}
}
4. Restart Claude Code/Desktop
5. Verify MCP Connection
Ask Claude: "Can you list the available DevOps practices from the MCP server?"
π‘ Tip: Claude may need a reminder to check the MCP. If it doesn't respond with practice names, try:
- "Please verify you can access the devops-practices MCP server"
- "List all available MCP tools"
- Restart Claude Code again
π§ͺ Experimental / Testing (For Nerds)
β οΈ Note: These methods are experimental and not yet fully tested. Use Manual Installation (above) for reliable setup.
Option 1: MCP Registry via Claude Desktop UI (Experimental):
- Open Claude Desktop
- Go to Settings β Developer β MCP Servers
- Search for "devops-practices"
- Click "Install"
- Restart Claude Code/Desktop
Option 2: Install via uvx (β¨ Recommended - automatic venv):
# Add MCP server using uvx (handles venv automatically)
claude mcp add devops-practices -- uvx devops-practices-mcp
# Restart Claude Code/Desktop to activate
Why recommended: uvx automatically manages the virtual environment for you - no setup needed.
Option 3: Install with uv + venv (For Python developers):
# Install uv if you don't have it
curl -LsSf https://astral.sh/uv/install.sh | sh
# Create virtual environment
uv venv ~/.venvs/devops-practices-mcp
# Activate venv
source ~/.venvs/devops-practices-mcp/bin/activate
# Install MCP server
uv pip install devops-practices-mcp
# Add to Claude configuration (using venv's python)
claude mcp add devops-practices -- ~/.venvs/devops-practices-mcp/bin/python -m devops_practices_mcp
# Restart Claude Code/Desktop to activate
Why use this: Full control over the virtual environment with modern uv tooling.
Option 4: Install to user directory (Legacy - no venv):
# Install using pip (to ~/.local/)
pip install --user devops-practices-mcp
# Add to Claude configuration
claude mcp add devops-practices -- python3 -m devops_practices_mcp
# Restart Claude Code/Desktop to activate
Option 5: Install system-wide (Requires sudo):
# Install system-wide (requires root)
sudo pip install devops-practices-mcp
# Add to Claude configuration
claude mcp add devops-practices -- python3 -m devops_practices_mcp
# Restart Claude Code/Desktop to activate
Option 6: Manual configuration (Edit config files directly):
Install via pip or uvx, then edit ~/.claude/config.json:
{
"mcpServers": {
"devops-practices": {
"command": "uvx",
"args": ["devops-practices-mcp"],
"env": {}
}
}
}
Real-World Use Cases
1. Multi-Environment Kafka Deployment
Scenario: Deploying Kafka across dev β test β uat β prod
Without MCP:
- Duplicate 580-line CLAUDE.md in each project
- Repeat same issues on each environment (12 hours total)
- No standardized approach across teams
With MCP:
- Claude queries
get_practice("configuration-management")for installation SOPs - Copies dev runbook for test environment (56% time savings)
- All teams follow same standards automatically
Result: 5.25 hours vs 12 hours (56% faster)
2. Standardized Git Workflow
Scenario: Team needs consistent branching strategy
Without MCP:
- Each project has different branching approach
- New team members confused about workflow
- Git practices documented differently everywhere
With MCP:
- Claude queries
get_practice("02-01-git-practices") - Everyone gets same 200+ line GitLab Flow documentation
- Single source of truth for git standards
Result: Consistent workflow across all 15 projects
3. Air-Gapped Infrastructure Deployment
Scenario: Deploying to secure environment without internet
Without MCP:
- Re-explain workflow every session
- Copy-paste commands from old runbooks
- Inconsistent file transfer procedures
With MCP:
- Claude queries
get_practice("air-gapped-workflow") - Gets step-by-step: Laptop β S3 β Bastion β Target
- Consistent process every time
Result: Zero security incidents, predictable deployments
4. Project Documentation Setup
Scenario: Starting new infrastructure project
Without MCP:
- Create CLAUDE.md from scratch (2 hours)
- Copy-paste from old projects (inconsistent)
- Miss important practices
With MCP:
User: "Create project structure for monitoring-stack project"
Claude: [Queries MCP for templates]
Claude: Creates TRACKER.md, CURRENT-STATE.md, RUNBOOK.md
All following latest standards
Result: 15 minutes vs 2 hours (88% faster)
5. Issue Tracking for Complex Projects
Scenario: Managing 50+ work items across 3-month project
Without MCP:
- Use external Jira (access issues, overhead)
- Or track in scattered markdown files
- No consistent format
With MCP:
- Claude queries
get_template("ISSUES") - Creates in-repo issue tracking with dashboard
- Uses
tools/issue-manager.shfor CLI management
Result: Git-based tracking, no external dependencies
Usage Examples
For Claude
When working on your projects:
Query Practice:
User: "What's the air-gapped workflow for file transfers?"
Claude: [Queries MCP: get_practice("air-gapped-workflow")]
Claude: [Receives markdown content]
Claude: "Here's the air-gapped workflow..."
Get Template (Raw):
User: "Show me the TRACKER template"
Claude: [Queries MCP: get_template("TRACKER-template")]
Claude: [Receives template with ${VARIABLES}]
Claude: "Here's the template..."
Render Template (With Variables):
User: "Create a TRACKER.md for my kafka-deployment project"
Claude: [Queries MCP: render_template("TRACKER-template", {
"PROJECT_NAME": "kafka-deployment",
"DATE": "2026-02-14",
"PHASE_NAME": "UAT Deployment"
})]
Claude: [Receives rendered template with all variables substituted]
Claude: [Creates TRACKER.md with actual values]
Updating Practices
For Contributors:
cd devops-practices-mcp
vim practices/documentation-standards.md
# Make changes
git add practices/documentation-standards.md
git commit -m "Update documentation standards: add new RUNBOOKS guidelines"
git push
# All projects using this MCP server now get updated standards
Branching Strategy
This repository uses GitLab Flow with semantic versioning to ensure stability for dependent projects.
Branch Structure
main β Production releases only (v1.0.0, v1.1.0, etc.)
β
develop β Active development, integration branch
β
feature/* β New practices, templates
release/* β Version preparation (v1.2.0)
hotfix/* β Critical production fixes
Branch Types
| Branch | Purpose | Created From | Merges To |
|---|---|---|---|
main | Production releases (tagged) | - | - |
develop | Active development | main | main (via release) |
feature/* | New functionality | develop | develop |
release/* | Version preparation | develop | main + develop |
hotfix/* | Critical fixes | main | main + develop |
Why GitLab Flow?
- β
Stability:
mainalways contains tested, production-ready code - β
Safety: Changes go through
developbefore reaching production - β Testing: CI/CD validates all changes before merge
- β Versioning: Clear semantic version releases (v1.0.0, v1.1.0, etc.)
- β Traceability: Full history of what changed and when
Quick Workflows
Add New Practice/Template:
git checkout develop
git checkout -b feature/add-security-practice
# Make changes, commit
git push origin feature/add-security-practice
# Create PR β develop
Create Release:
git checkout develop
git checkout -b release/v1.2.0
# Update CHANGELOG.md, version numbers
# Create PR β main
# Tag release: git tag v1.2.0
# Merge back to develop
Critical Hotfix:
git checkout main
git checkout -b hotfix/critical-bug
# Fix, commit, push
# Create PR β main (fast-track)
# Also merge to develop
Full Documentation: See CONTRIBUTING.md and git-practices.md
Governance
Who Maintains This
- Owner: Uttam Jaiswal Lead
- Contributors: DevOps Engineers
- Review Process: PR required for changes
Update Protocol
For New Practices/Templates:
- Create feature branch from
develop - Update practice or template files
- Run health check:
bash health-check.sh - Update documentation (README.md, PRACTICE-INDEX.md)
- Create PR with description β
develop - Code review by team
- Merge to
developafter CI/CD passes
For Releases:
- Create release branch from
develop:release/v1.x.0 - Update CHANGELOG.md and version numbers
- Create PR β
main - Tag release after merge:
git tag v1.x.0 - Merge release back to
develop - Announce to team (affects all dependent projects)
For Critical Fixes:
- Create hotfix branch from
main:hotfix/issue-name - Fix issue and test thoroughly
- Create PR β
main(fast-track approval) - Tag hotfix release:
git tag v1.x.1 - Merge to
developto keep in sync - Announce urgent fix to team
See: CONTRIBUTING.md for detailed workflows
Versioning
- Major version (2.0): Breaking changes to structure
- Minor version (1.1): New practices added
- Patch version (1.0.1): Clarifications, fixes
Projects Using This MCP Server
| Project | Purpose | Location |
|---|---|---|
| kafka-deployment | Apache Kafka deployment | Example project |
| observability-stack | Observability stack | Example project |
| network-infra | Network infrastructure | Example project |
Development
See CONTRIBUTING.md for detailed contribution workflow, branching strategy, and code review process.
Adding a New Practice
- Create markdown file in
practices/ - Use clear structure with examples
- Update
mcp-server.pyif needed - Test with Claude
- Update this README (practice count)
- Update PRACTICE-INDEX.md (add to scenario lists)
- Update CHANGELOG.md (document the addition)
- Run health check:
bash health-check.sh
Adding a New Template
- Create template file in
templates/ - Use placeholders:
${PROJECT_NAME},${DATE}, etc. (see auto-provided variables in MCP Tools section) - No code changes needed -
render_templatehandles all${...}substitutions automatically - Test template:
render_template("your-template", {"VAR": "value"}) - Update this README (template count)
- Update CHANGELOG.md (document the addition)
- Run health check:
bash health-check.sh
Making Changes
- Before release: Run health check to validate all files
- After changes: Update CHANGELOG.md with version bump
- Breaking changes: Update MIGRATION-GUIDE.md with migration notes
- New features: Update PRACTICE-INDEX.md with usage scenarios
Troubleshooting
Claude Can't Access MCP Server
Symptoms: Claude doesn't return practices when asked, or acts like MCP doesn't exist
Solutions:
- Remind Claude explicitly: "Please check the devops-practices MCP server and list available practices"
- Verify MCP is loaded: Ask "What MCP servers do you have access to?"
- Check configuration: Verify
~/.claude/config.jsonhas correct paths (must be absolute paths) - Restart Claude Code: MCP servers load on startup
- Check logs: Look at
~/.cache/claude/mcp-devops-practices.logfor errors - Verify MCP process: Run
ps aux | grep mcp-server.pyto confirm it's running
π‘ Pro Tip: Claude sometimes "forgets" to check MCP servers. Explicitly remind it to verify the MCP before proceeding with tasks.
Log location: ~/.cache/claude/mcp-devops-practices.log
MCP Server is Down or Unavailable
Symptoms: MCP server process crashed, not responding, or cannot start
Fallback Options:
Option 1: GitHub Practices (Recommended)
Access practices directly from GitHub:
https://github.com/ai-4-devops/devops-practices/tree/main/practices
Ask Claude to read practices via GitHub URLs when MCP unavailable.
Option 2: Local Clone
# Access practices from local clone
ls ~/.mcp-servers/devops-practices-mcp/practices/
# Read practice directly
cat ~/.mcp-servers/devops-practices-mcp/practices/03-02-air-gapped-workflow.md
Option 3: CLAUDE.md Appendix
Projects using the CLAUDE-template.md have a built-in appendix
with critical practice summaries for emergency fallback.
See: templates/CLAUDE-template.md (Appendix section)
Prevention:
- Use .mcp.json for project-level config (more reliable)
- Add MCP health check to pre-session checklist
- Keep local clone updated:
git pull origin main - Monitor logs:
tail -f ~/.cache/claude/mcp-devops-practices.log
Related: MIGRATION-GUIDE.md for project-specific fallback setup
Practice File Not Found
- Verify file exists:
ls practices/ - Check filename matches exactly (case-sensitive)
- Check MCP server logs
Template Substitution Failing
- Verify placeholder syntax:
${VARIABLE} - Check template file encoding (UTF-8)
- Review mcp-server.py logs
License
MIT License - Free to use and modify
Maintained By: Uttam Jaiswal Last Updated: 2026-02-20 Version: 1.4.0
