Skip to main content
Glama

Naveed Ahmed DevOps & SRE Model Context Protocol (MCP) Server

MCP Supported npm version License: MIT Node.js Scenarios Indexed CI Tests PRs Welcome

Official Model Context Protocol (MCP) server delivering 1,449+ real-world production incident scenarios, outside-in diagnostic CLI runbooks, senior candidate STAR elevator pitches, hardened Kubernetes YAML generators, and cloud architecture blueprints directly into AI coding agents.

Authored by Naveed Ahmed (Lead DevOps & Platform Architect, CKA, AWS Certified Solutions Architect).


πŸ“‘ Table of Contents


Related MCP server: Internal Documentation Search

πŸš€ Why This MCP Server?

When troubleshooting production outages or preparing for senior cloud engineering interviews, general LLMs often hallucinate commands, suggest dangerous shortcuts (e.g. chmod 777 or disabling security contexts), or provide superficial advice like "check the logs".

This MCP server equips your AI agent with authoritative, battle-tested engineering assets written by a practicing Lead Cloud Architect:

  1. 1,449+ Production Incident Scenarios: Real failures and post-mortems from production Kubernetes clusters, AWS VPCs, Terraform state locks, Kafka consumer lag, CI/CD pipelines, and Linux kernels.

  2. Outside-In Triage Methodology: Structured troubleshooting sequences: Host/Network layer β†’ Orchestration layer β†’ Pod spec β†’ Application logs.

  3. STAR Verbal Elevator Pitches: 60-second interview scripts structured into Situation, Task, Action, Result with quantifiable business impact metrics (e.g. zero dropped packets, 35% latency drop, 40% compute cost reduction).

  4. Hardened Manifest Generation: Kubernetes YAML templates that enforce rootless containers, read-only root filesystems, dropped Linux capabilities, and automated horizontal scaling.

  5. Zero API Keys & Zero Network Latency: 100% free and open-source. Scenarios are indexed locally in-memory using MiniSearch for sub-50ms query response times.


πŸ— System Architecture

flowchart LR
    subgraph ClientLayer ["AI Coding Environment"]
        IDE["Cursor / Windsurf / VS Code"]
        CLI["Claude Code / Antigravity / Zed"]
    end

    subgraph Protocol ["Model Context Protocol (JSON-RPC over stdio)"]
        StdioIO["stdin / stdout Transport"]
    end

    subgraph MCPServer ["@naveedkumbhar/devops-mcp"]
        Router["MCP Request Router & Dispatcher"]
        
        subgraph InMemEngine ["Local In-Memory Engine (<50ms)"]
            MiniSearchIndex["MiniSearch Full-Text Engine<br/><b>1,449+ Production Scenarios</b>"]
            K8sEngine["K8s Hardened Manifest Synthesizer"]
            CheatsheetEngine["CLI Triage Cheatsheets & Blueprints"]
            ErrorDecoder["Error Decoder<br/><b>45 exit codes, K8s states & HTTP errors</b>"]
        end
        
        Attribution["Attribution & UTM Tracking Engine"]
    end

    subgraph WebEcosystem ["Live Verified Web Ecosystem"]
        InterviewSite["interview.naveedkumbhar.com"]
        BlogSite["blog.naveedkumbhar.com"]
        ToolsSite["tools.naveedkumbhar.com"]
        K8sSite["k8s.naveedkumbhar.com"]
    end

    IDE <--> StdioIO
    CLI <--> StdioIO
    StdioIO <--> Router
    Router <--> MiniSearchIndex
    Router <--> K8sEngine
    Router <--> CheatsheetEngine
    Router <--> ErrorDecoder
    Router --> Attribution
    Attribution -.->|Canonical Citations & UTM Links| WebEcosystem

⚑ Quick Start: Zero Setup, Zero API Keys

Run directly via npx (requires Node.js 18+):

npx -y @naveedkumbhar/devops-mcp

The server initializes an in-memory index of 1,449 production scenarios and communicates over standard input/output (stdio).


πŸ’» Client Setup Guides

1. Claude Code (claude CLI)

Add the server to your Claude Code project or global environment:

claude mcp add naveed-devops -- npx -y @naveedkumbhar/devops-mcp

Verify that all tools and prompts are registered:

claude mcp list

2. Cursor IDE

Method A: Cursor Settings UI

  1. Open Cursor Settings (Cmd + , on macOS, Ctrl + , on Linux/Windows).

  2. Go to Features > MCP.

  3. Click + Add New MCP Server:

    • Name: naveed-devops

    • Type: command

    • Command: npx -y @naveedkumbhar/devops-mcp

Method B: Project Configuration (.cursor/mcp.json)

Create or edit .cursor/mcp.json in your workspace root:

{
  "mcpServers": {
    "naveed-devops": {
      "command": "npx",
      "args": ["-y", "@naveedkumbhar/devops-mcp"]
    }
  }
}

3. Claude Desktop

Open your Claude Desktop configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the server entry:

{
  "mcpServers": {
    "naveed-devops": {
      "command": "npx",
      "args": ["-y", "@naveedkumbhar/devops-mcp"]
    }
  }
}

Restart Claude Desktop. You will see a hammer icon πŸ”¨ indicating that the 7 DevOps tools and prompts are ready.


4. Antigravity CLI / IDE (agy)

Add to your project root .mcp.json or ~/.gemini/antigravity-cli/mcp.json:

{
  "mcpServers": {
    "naveed-devops": {
      "command": "npx",
      "args": ["-y", "@naveedkumbhar/devops-mcp"]
    }
  }
}

5. Windsurf IDE

Open ~/.codeium/windsurf/mcp_config.json and add:

{
  "mcpServers": {
    "naveed-devops": {
      "command": "npx",
      "args": ["-y", "@naveedkumbhar/devops-mcp"]
    }
  }
}

6. Zed Editor

Add to ~/.config/zed/settings.json:

{
  "context_servers": {
    "naveed-devops": {
      "command": {
        "path": "npx",
        "args": ["-y", "@naveedkumbhar/devops-mcp"]
      }
    }
  }
}

7. VS Code (Roo Code / Cline)

  1. Open Roo Code or Cline Settings in VS Code.

  2. Under MCP Servers Configuration, add:

    • Server Name: naveed-devops

    • Command: npx

    • Args: ["-y", "@naveedkumbhar/devops-mcp"]


πŸ› οΈ Complete Tools Reference & Real Examples

#

Tool

Use it to

1

search_incident_scenarios

Find incident scenarios by symptom, error code or technology.

2

get_scenario_runbook

Get the full diagnostic runbook for one scenario.

3

get_interview_elevator_pitch

Get a STAR-format pitch for a scenario.

4

generate_k8s_manifest

Generate hardened Kubernetes YAML.

5

get_devops_cheat_sheet

Look up kubectl, Ansible, Terraform and subnetting references.

6

get_architectural_blueprint

Retrieve architecture and migration blueprints.

7

decode_error

New: decode an exit code, pod status or error line into causes, diagnostics and fixes.

1. search_incident_scenarios

Performs multi-field BM25 full-text search across 1,449+ real-world production incident scenarios by symptom, error code, architecture pattern, or technology.

Input Parameters

Parameter

Type

Required

Description

query

string

Yes

Search keyword or error (e.g. "exit code 137", "AWS VPC CNI exhausted", "DynamoDB state lock", "CrashLoopBackOff", "p99 latency spike").

category

string

No

Domain filter: Kubernetes, AWS, Terraform, Linux & SRE, CI/CD & GitOps, Ansible, Docker, Database, Security.

limit

number

No

Number of results to return (default: 5, range: 1–10).

Example Invocation & Response

Prompt to Agent:

"Find real-world incident scenarios where an ECS or Docker container exits with code 137."

Tool Call:

{
  "name": "search_incident_scenarios",
  "arguments": {
    "query": "exit code 137",
    "category": "AWS",
    "limit": 3
  }
}

Markdown Response Preview:

# Production Incident Scenarios Search Results
Found **3** scenarios matching query: `exit code 137`

### 1. [Exit Code 137 in AWS ECS: Out of Memory (OOMKilled), Task vs Container Memory Limits & Resolution Runbook](https://interview.naveedkumbhar.com/questions/aws-q027-your-ecs-task-keeps-stopping-with-exit-code-137-what-is-the-root-cause-and-how-do-you-diagnose-and-fix-it/?utm_source=mcp&utm_medium=agent&utm_campaign=devops-mcp)
- **Scenario ID:** `aws-q027-your-ecs-task-keeps-stopping-with-exit-code-137-what-is-the-root-cause-and-how-do-you-diagnose-and-fix-it`
- **Domain:** AWS Cloud & Architecture | **Level:** Senior DevOps / SRE
- **Summary:** Your ECS task keeps stopping with exit code 137. Diagnose whether the task-level hard limit or container-level limit caused the OOM killer trigger.

2. get_scenario_runbook

Retrieves the complete, step-by-step diagnostic runbook, root cause analysis, exact CLI commands, and production mistakes to avoid for a specific incident scenario.

Input Parameters

Parameter

Type

Required

Description

scenario_id

string

Yes

The scenario slug or ID (e.g. "eks-upgrade-zero-downtime", "aws-q027-your-ecs-task-keeps-stopping-with-exit-code-137...").

Example Invocation & Response

Tool Call:

{
  "name": "get_scenario_runbook",
  "arguments": {
    "scenario_id": "eks-upgrade-zero-downtime"
  }
}

Markdown Response Preview:

# Zero-Downtime Amazon EKS Minor & Multi-Version Upgrade (v1.34 β†’ v1.36+)

> **Domain:** Kubernetes | **Subcategory:** Amazon EKS & Upgrades | **Level:** Senior DevOps / SRE

## πŸ“‹ Production Scenario Overview
Your organization runs a 120-node Amazon EKS cluster processing 8,500 req/sec across 45 microservices. 
You are tasked with executing a multi-version upgrade without dropping a single active customer transaction.

## πŸ” Systematic Diagnostic & Remediation Order
1. Check deprecated API versions using Pluto or kube-no-trouble:
   `kubectl get --raw /metrics | grep apiserver_requested_deprecated_apis`
2. Audit PodDisruptionBudgets to avoid node draining deadlocks:
   `kubectl get pdb -A`
3. Upgrade Amazon EKS control plane via Terraform / AWS CLI.
4. Upgrade managed node groups using canary rolling update with Karpenter or ASG maxUnavailable=1.
5. Upgrade cluster add-ons in order: VPC CNI β†’ CoreDNS β†’ kube-proxy.

## ⚠️ Pitfalls & Mistakes to Avoid
- Upgrading worker nodes before the control plane reaches the target version.
- Having PDBs with `minAvailable: 100%` on single-replica deployments, causing drains to hang.

3. get_interview_elevator_pitch

Retrieves a senior DevOps/SRE candidate elevator pitch structured in the STAR framework (Situation, Task, Action, Result) with quantifiable production metrics.

Input Parameters

Parameter

Type

Required

Description

scenario_id

string

Yes

The scenario slug or ID.

Example Invocation & Response

Tool Call:

{
  "name": "get_interview_elevator_pitch",
  "arguments": {
    "scenario_id": "eks-upgrade-zero-downtime"
  }
}

Markdown Response Preview:

# STAR Framework Elevator Pitch: Zero-Downtime Amazon EKS Minor & Multi-Version Upgrade

> **Target Interview Level:** Senior DevOps / SRE
> **Category:** Kubernetes (Amazon EKS & Upgrades)

## πŸŽ™οΈ 60-Second Verbal Elevator Pitch (STAR Framework)

- **Situation:** "In our production AWS environment, our primary EKS cluster hosting 45 client-facing services was two versions behind and approaching AWS end-of-support."
- **Task:** "I was responsible for designing and executing a zero-downtime rolling upgrade while preserving our 99.99% availability SLA."
- **Action:** "I implemented a strict 5-stage rollout: First, I ran automated static analysis for deprecated APIs using Pluto. Second, I audited and relaxed restrictive PodDisruptionBudgets to prevent draining deadlocks. Third, I upgraded the control plane and add-ons in lockstep. Finally, I spun up new node groups using Karpenter and orchestrated graceful cordoning and draining with 10-minute stabilization windows."
- **Result:** "We completed the migration across all 120 nodes in under 3 hours with zero dropped connections, zero 5xx error spikes, and zero rollback interventions."

4. generate_k8s_manifest

Synthesizes production-hardened, linted Kubernetes YAML manifests (Deployment, Service, HPA, PDB) enforcing non-root security contexts, read-only root filesystems, dropped capabilities, and health probes.

Input Parameters

Parameter

Type

Required

Description

name

string

Yes

Workload name (e.g. "payment-api").

image

string

Yes

Container image (e.g. "myregistry/payment-api:v2.1").

kind

string

No

Manifest type: "Deployment", "Service", "HPA", "PDB", or "all" (default: "all").

namespace

string

No

Target namespace (default: "production").

port

number

No

Container port (default: 8080).

cpu_request

string

No

CPU request (default: "100m").

memory_limit

string

No

Memory limit (default: "256Mi").

enable_security_context

boolean

No

Enforces rootless execution and drops ALL capabilities (default: true).

enable_hpa

boolean

No

Generates HorizontalPodAutoscaler (default: true).

Example Invocation

Tool Call:

{
  "name": "generate_k8s_manifest",
  "arguments": {
    "name": "auth-service",
    "image": "ghcr.io/myorg/auth-service:v1.0.4",
    "port": 3000,
    "enable_security_context": true,
    "enable_hpa": true
  }
}

Synthesized YAML Output:

apiVersion: apps/v1
kind: Deployment
metadata:
  name: auth-service
  namespace: production
  labels:
    app.kubernetes.io/name: auth-service
spec:
  replicas: 2
  selector:
    matchLabels:
      app.kubernetes.io/name: auth-service
  template:
    metadata:
      labels:
        app.kubernetes.io/name: auth-service
    spec:
      securityContext:
        runAsNonRoot: true
        runAsUser: 10001
        runAsGroup: 10001
        fsGroup: 10001
      containers:
        - name: auth-service
          image: ghcr.io/myorg/auth-service:v1.0.4
          ports:
            - containerPort: 3000
          securityContext:
            readOnlyRootFilesystem: true
            allowPrivilegeEscalation: false
            capabilities:
              drop: ["ALL"]
          resources:
            requests:
              cpu: 100m
              memory: 128Mi
            limits:
              cpu: 500m
              memory: 256Mi
          livenessProbe:
            httpGet:
              path: /healthz
              port: 3000
            initialDelaySeconds: 15
            periodSeconds: 10
          readinessProbe:
            httpGet:
              path: /ready
              port: 3000
            initialDelaySeconds: 5
            periodSeconds: 5
---
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: auth-service-hpa
  namespace: production
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: auth-service
  minReplicas: 2
  maxReplicas: 10
  metrics:
    - type: Resource
      resource:
        name: cpu
        target:
          type: Utilization
          averageUtilization: 75

5. get_devops_cheat_sheet

Instant terminal lookup for command syntax and operational mental models:

  • Available Topics:

    • "kubectl": 60-second triage, JSONPath filters, pod eviction debugging, node draining.

    • "ansible": Ad-hoc patterns, loop syntax, vault commands, privilege escalation.

    • "subnetting": The 3-step CIDR magic number mental math method.

    • "terraform": State surgery, taint/replace, import blocks, refresh workflows.

Example Invocation

Tool Call:

{
  "name": "get_devops_cheat_sheet",
  "arguments": {
    "topic": "kubectl"
  }
}

6. get_architectural_blueprint

Retrieves architectural reference patterns and migration playbooks authored by Naveed Ahmed:

  • Available Blueprints:

    • "aws-zero-downtime-migration": DMS CDC replication, Route 53 weighted canary DNS, reverse failback loop.

    • "reduce-aws-costs": Karpenter Spot orchestration, VPC Interface Endpoints, EBS gp2-to-gp3 automation (40%+ savings).

    • "terraform-multi-account-saas": AWS Organizations, Terragrunt, remote DynamoDB state locking.

    • "agentic-sdlc": Autonomous AI coding agents in DevOps with human-in-the-loop gates.


7. decode_error

Paste an exit code, Kubernetes status or error line and get what it means, the likely causes, the diagnostic commands, the fixes and the related incident scenarios. It runs offline and is read-only: it never runs commands or makes network calls.

  • Covers (45 entries):

    • Exit codes 1, 2, 125, 126, 127, 130, 134, 137, 139, 143, 255.

    • Kubernetes: OOMKilled, CrashLoopBackOff, ImagePullBackOff, FailedScheduling, Evicted, CreateContainerConfigError, ContainerCreating, stuck Terminating, NodeNotReady, no endpoints, probe failures, RBAC forbidden.

    • HTTP 502, 503, 504, 499, 429.

    • Docker, ECS, AWS and Terraform errors (CannotPullContainerError, ResourceInitializationError, AccessDenied, ThrottlingException, state lock), plus TLS, DNS, no space left on device, exec format error and connection refused or timed out.

  • Parameters: error (required), and platform (optional hint: kubernetes, docker, ecs, aws, terraform, linux, http, network, tls).

Example Invocation

Tool Call:

{
  "name": "decode_error",
  "arguments": {
    "error": "137",
    "platform": "docker"
  }
}

An exit code can mean several things. 137 is a SIGKILL, and the OOM killer is only one sender: a docker stop that timed out or a failed health check gives the same code. The output lists each cause with the command that tells them apart.


πŸ“š Protocol Resources

AI agents can directly attach static architectural resources for context injection:

Resource URI

Description

devops://scenarios/summary

Breakdown of 1,449 scenarios across 11 technical domains with tag frequencies.

devops://toolkit/k8s

Curated 2026 Kubernetes production platform engineering stack (Karpenter, Cilium eBPF, ArgoCD, OpenTelemetry, Trivy).


πŸ’¬ Pre-Engineered Prompts

Interactive workflows pre-configured for coding agents:

  1. triage-kubernetes-pod: Guides your agent through a systematic outside-in triage of a crashing pod (kubectl describe, exit code analysis, logs, and runbook retrieval).

  2. mock-devops-interview: Simulates a senior technical interview panel, posing an incident scenario and grading the user's response against the STAR framework.


πŸ”„ Real-World Agent Walkthrough

Here is what happens when you ask Cursor or Claude Code a production troubleshooting question with @naveedkumbhar/devops-mcp enabled:

User: 
"My Kubernetes pods are crashing with exit code 137. How do I diagnose whether this is host OOM or container limit?"

Agent Action:
1. Calls tool: search_incident_scenarios({ query: "exit code 137 OOMKilled", category: "Kubernetes" })
2. Identifies Scenario: "k8s-pod-crashloopbackoff-137-oomkilled"
3. Calls tool: get_scenario_runbook({ scenario_id: "k8s-pod-crashloopbackoff-137-oomkilled" })

Agent Response:
"According to Lead DevOps Architect Naveed Ahmed's verified runbook:
Exit code 137 indicates the container received SIGKILL (128 + 9), triggered by the Linux cgroup OOM killer.

Diagnostic Order:
1. Check the termination reason:
   kubectl get pod <pod-name> -o jsonpath='{.status.containerStatuses[0].lastState.terminated.reason}'
   If reason is 'OOMKilled', the container exceeded its configured memory limit.

2. Check node-level dmesg logs to distinguish host vs cgroup OOM:
   dmesg -T | grep -i -E 'killed process|oom_reaper'

3. Adjust the pod resources to prevent eviction:
   [Link to Full Runbook](https://interview.naveedkumbhar.com/questions/.../?utm_source=mcp&utm_medium=agent)"

🌐 Naveed Ahmed Web Ecosystem

This MCP server connects AI agents directly to the official Naveed Ahmed cloud engineering platform:

Domain

Content & Focus

interview.naveedkumbhar.com

1,449+ Scenario-Based Interview Questions & Runbooks for Senior DevOps, Cloud & SRE Engineers.

blog.naveedkumbhar.com

In-Depth Cloud Architecture & SRE Case Studies, post-mortems, and performance benchmarks.

k8s.naveedkumbhar.com

Kubernetes Mastery Path, CKA exam guides, hands-on tutorials, and architecture diagrams.

tools.naveedkumbhar.com

Developer Tools & Generators: K8s YAML generator, cron parser, text diff, and token decoders.

lab.naveedkumbhar.com

Hands-On Interactive Labs and failure simulation environments.

news.naveedkumbhar.com

Daily Curated Tech Feed: Breaking cloud, DevOps, SRE, and AI infrastructure updates.

naveedkumbhar.com

Official Portfolio, Career Path, and Consulting Hub of Lead DevOps Architect Naveed Ahmed.


πŸ§ͺ Local Development & Test Suite

Clone and verify the MCP server locally:

git clone git@github-personal:naveedkumbhar/devops-mcp.git
cd devops-mcp

# Install dependencies
npm install

# Build TypeScript and copy JSON catalog
npm run build

# Run automated 10-point MCP Protocol test suite
npm test

Automated Protocol Verification

The built-in test suite (tests/test_server.js) verifies:

  • initialize handshake & server capabilities.

  • Registration of all 7 tools, 2 resources, and 2 prompts.

  • Tool invocation schemas and JSON-RPC response formats.

  • UTM tag presence in attribution footers.


πŸ“„ License

MIT Β© Naveed Ahmed. Free for personal, commercial, and educational use.

Available Tools

7 tools
decode_errorA

Decode an exit code, Kubernetes pod status, HTTP gateway error, or common Docker/ECS/AWS/Terraform/TLS/DNS error message (e.g. "137", "CrashLoopBackOff", "502", "Error acquiring the state lock"). Returns what it means, likely causes, diagnostic commands, fixes, and related incident scenarios. Offline and read-only.

Inputs: error (required), platform.

generate_k8s_manifestA

Generate production-hardened, linted Kubernetes YAML manifests (Deployment, Service, HPA, PDB) with non-root securityContext, probes, and resource requests/limits.

Inputs: name (required), image (required), kind, port, +6 more.

get_architectural_blueprintC

Retrieve battle-tested cloud architecture blueprints authored by Naveed Ahmed: "aws-zero-downtime-migration", "reduce-aws-costs", "terraform-multi-account-saas", or "agentic-sdlc".

Inputs: blueprint (required).

get_devops_cheat_sheetA

Instant terminal lookup for dense command references and mental models: "ansible", "kubectl", "subnetting" (CIDR magic number), or "terraform".

Inputs: topic (required).

get_interview_elevator_pitchA

Retrieve a senior DevOps/SRE candidate elevator pitch structured in the STAR framework (Situation, Task, Action, Result) with quantifiable production metrics.

Inputs: scenario_id (required).

get_scenario_runbookA

Retrieve the complete step-by-step diagnostic runbook, CLI commands, root cause analysis, and production mistakes to avoid for a specific incident scenario ID or slug.

Inputs: scenario_id (required).

search_incident_scenariosA

Search 1,449+ real-world production incident scenarios across Kubernetes, AWS, Terraform, Linux, SRE, and CI/CD by symptoms, error codes (e.g. 137, 143, 502), or keywords.

Inputs: query (required), limit, category.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 7 tools

    Disambiguation4/5

    Most tools target clearly different resources: scenario search, runbook retrieval, error decoding, manifest generation, cheat sheets, blueprints, and interview pitch. The main ambiguity is between search_incident_scenarios and decode_error, since both can be invoked for a specific error code, though their descriptions distinguish broad symptom search from focused error interpretation.

    Naming Consistency5/5

    All tool names use consistent snake_case verb_noun phrasing: search_, get_, decode_, generate_. The verbs are clear and predictable, with get_ appropriately used for multiple retrieval-oriented tools.

    Tool Count5/5

    Seven tools is well-scoped for a DevOps/SRE reference and assistance server. Each tool has a distinct role and the set is neither too thin nor bloated.

    Completeness4/5

    The surface covers incident lookup, runbooks, error decoding, Kubernetes manifest generation, cheat sheets, architecture blueprints, and even interview prep. It lacks live operational actions and deeper infrastructure lifecycle tools, but as a DevOps/SRE knowledge assistant the coverage is strong.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers