pipeline-assistant

🚀 AI-powered CI/CD pipeline analyzer for Azure DevOps & GitHub. Automatically enforces security policies, detects vulnerabilities, and posts compliance reports on PRs. Open source DevSecOps automation.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio soydachi-pipeline-assistant-mcp node dist/server.js \
  --env PORT="default 3000 (or as configured in dist/server.js)" \
  --env NODE_ENV="production (or placeholder)"

How to use

Pipeline Assistant MCP is an AI-powered helper that uses the Model Context Protocol to automate and optimize CI/CD pipelines. It can generate production-ready pipelines from templates, enforce security policies automatically, analyze existing pipelines for vulnerabilities, and provide actionable improvement suggestions. You can interact with the MCP server via its CLI and generated tooling to create pipelines for platforms like Azure DevOps and GitHub Actions, apply SEC-001 to SEC-010 policies, and receive a compliance score along with SBOM generation.

How to install

Prerequisites:

Node.js 20+ and npm 9+ (as indicated by the project requirements)
Git

Clone the repository

git clone https://github.com/soydachi/pipeline-assistant-mcp.git
cd pipeline-assistant-mcp

Install dependencies

npm install

Build the project (if a build step is required by the repo)

npm run build

Run tests (optional but recommended)

npm test

Start the MCP server (example: in development or after build)

node dist/server.js

Notes:

The exact start command may vary if you use a different entry point or a Docker image; adjust the command accordingly once you have a built distribution.
If you prefer Docker, follow the Docker-based deployment steps once a container image is available from the project maintainers.

Additional notes

Tips and common considerations:

Review the corporate standards (v2.0) in the wiki/standards directory to understand supported policies and templates.
When using the MCP server, you can generate pipelines for multiple platforms (Azure DevOps and GitHub Actions) and templates (NET, Node, Python, Java, Go).
Ensure environment variables (like PORT) are set appropriately in your deployment environment if not using the default.
Monitor the Compliance Score output to gauge security posture; SBOM generation is included as part of the pipeline artifacts.
If you encounter port conflicts, configure the PORT environment variable to an open port in your environment.

Related MCP Servers

jenkins -enterprise

The most advanced Jenkins MCP server available - Enterprise debugging, multi-instance management, AI-powered failure analysis, vector search, and configurable diagnostics for complex CI/CD pipelines.

mcp-jest

Automated testing for Model Context Protocol servers. Ship MCP Servers with confidence.

pentesting-cyber

🔐 50+ MCP Security Servers for AI-Powered Pentesting | Integrate Nmap, Burp Suite, Nuclei, Shodan, BloodHound, Semgrep, Trivy | Model Context Protocol for Cybersecurity

mcp-starter-template-ts

TypeScript starter template for building Model Context Protocol (MCP) servers, designed to help developers create secure and robust AI-agent-compatible services.

mcptrust

Runtime security proxy for MCP: lockfile enforcement, drift detection, artifact pinning, Sigstore/Ed25519 signing, CEL policy, OpenTelemetry tracing. Works with Claude Desktop, LangChain, AutoGen, CrewAI.

mcpscc

Security Command Center for Model Context Protocol (MCP) servers. Detect prompt injection, tool poisoning, secrets, and vulnerabilities. The Trivy of MCP security.