NOTE: This repository is an archival lab or partial prototype. It is not actively maintained and should not be used as a reference for production-grade deployments or performance benchmarks.

AI-Assisted DevSecOps Agent — MCP Server 🤖🔒

Maturity: Functional Prototype An MCP (Model Context Protocol) server exposing DevSecOps tooling to LLM clients.

⚠️ PoC Note: All tools return mock/simulated data — no live GitHub Actions, Jira, or logging integrations required. The MCP protocol implementation and tool structure are fully functional.

The Problem

DevSecOps teams drown in context-switching: checking pipeline status in one tab, triaging vulnerabilities in another, searching logs in a third. Meanwhile, LLM coding assistants can write code but are blind to your operational reality — they can't see your failing builds, open CVEs, or production errors.

Related MCP server: Talos MCP Server

The Solution

This MCP server bridges the gap by exposing four security-critical tools to any MCP-compatible LLM client (GitHub Copilot, Claude Desktop, Cursor, etc.):

Why This Over the Obvious Alternative

Most "AI + DevOps" demos are chatbots with hardcoded responses. This project implements the Model Context Protocol (MCP) — the open standard for tool-use that GitHub Copilot, Claude, and other major LLM clients natively support. The tools return real, structured data that the LLM reasons over, not canned answers.

Architecture

┌─────────────────┐     MCP (stdio/SSE)     ┌──────────────────────┐
│  LLM Client     │◄──────────────────────►│  MCP Server          │
│  (Copilot,      │                         │                      │
│   Claude, etc.) │                         │  ┌────────────────┐  │
│                 │                         │  │ Pipeline Tool   │  │
│                 │                         │  │ Vuln Triage Tool│  │
│                 │                         │  │ Log Search Tool │  │
│                 │                         │  │ Dep Scan Tool   │  │
│                 │                         │  └────────────────┘  │
└─────────────────┘                         └──────────────────────┘
                                                      │
                                              ┌───────┴───────┐
                                              │  Mock Data    │
                                              │  (Simulated   │
                                              │   APIs)       │
                                              └───────────────┘

🛠️ Tech Stack

• Runtime: Node.js + TypeScript

• Protocol: Model Context Protocol (MCP) SDK

• Transport: stdio (local) and SSE (remote)

• Containerization: Docker

🚀 Getting Started

Local Development

npm install
npm run build
npm run start

With Docker

docker-compose up -d --build

Connecting to Claude Desktop

Add to your Claude Desktop MCP config (claude_desktop_config.json):

{
  "mcpServers": {
    "devsecops-agent": {
      "command": "node",
      "args": ["dist/index.js"]
    }
  }
}

📁 Project Structure

src/
├── index.ts              # MCP Server entry point
├── tools/
│   ├── pipeline.tool.ts  # GitHub Actions pipeline status
│   ├── vulnerability.tool.ts  # CVE triage from mock board
│   ├── logs.tool.ts      # Log search across services
│   └── dependency.tool.ts # Dependency vulnerability scanning
└── data/
    └── mock-data.ts      # Simulated API responses

Decision Log

📋 Prerequisites

🚀 Step-by-Step Setup

Option A: Local Development

# 1. Clone the repository
git clone https://github.com/SumitDalavi/ai-devsecops-agent-mcp.git
cd ai-devsecops-agent-mcp

# 2. Install dependencies
npm install

# 3. Build the TypeScript project
npm run build

# 4. Start the MCP server (stdio transport)
npm run start

Option B: Docker

# 1. Clone and build
git clone https://github.com/SumitDalavi/ai-devsecops-agent-mcp.git
cd ai-devsecops-agent-mcp

# 2. Build and run
docker build -t devsecops-mcp-agent .
docker run -i devsecops-mcp-agent

Connecting to Claude Desktop

Add to your Claude Desktop config (claude_desktop_config.json):

{
  "mcpServers": {
    "devsecops-agent": {
      "command": "node",
      "args": ["/absolute/path/to/ai-devsecops-agent-mcp/dist/index.js"]
    }
  }
}

🧪 Usage & Demo

Once connected to an MCP client, you can ask natural language questions like:

The server returns structured JSON data that the LLM reasons over to provide contextual answers.

✅ Verification

# Verify the build succeeds
npm run build

# Verify the server starts (it will wait for MCP client connection on stdio)
node dist/index.js
# You should see: "DevSecOps MCP Agent running on stdio" on stderr

Mock Boundaries (Honest Scope)

📚 Documentation

• Architecture — System diagram and component details

• Runbook — Setup, commands, and expected outputs

• Decisions — ADRs for MCP integration

• Changelog — Change history

👨‍💻 Author

Sumit Dalavi — Senior DevSecOps / Platform Engineer GitHub | LinkedIn

Built with a focus on robust patterns, not toy demos.

CI & Reliability Updates (August 2026)

• CI Pipeline Remediation: Successfully resolved all CI/CD pipeline failures.

• Specific Fix: Upgraded Zod to match MCP SDK requirements and explicitly cast tool schemas to bypass TypeScript excessive type inference loop.

• Status: 🟩 Passing