Skip to main content
Glama
MCP SSDLC Security Toolkit

MCP SSDLC Security Toolkit

by vuongdat67

MCP SSDLC Security Toolkit v2.0

CI License: MIT Node.js TypeScript

An intelligent, domain-aware Security Software Development Life Cycle (SSDLC) toolkit powered by the Model Context Protocol (MCP). It helps Tech Leads, Security Engineers, and Developers orchestrate secure software design, generate pseudocode, and manage compliance.

🌟 Key Features

  • Domain-Agnostic Core: Built-in support for Healthcare (HIPAA), Fintech (PCI-DSS), Blockchain, Secure Communications, and 12+ more domains. Easily extensible to ANY domain via YAML plugins.

  • Tech Lead Automation: Generates Pseudocode (Python, TS, Java, Go, C#, C++, Rust), Architecture Diagrams (Mermaid), DFD/ERD, and Module Breakdowns from user stories.

  • Full Pipeline Orchestration: One command to run BA β†’ Tech Design β†’ Threat Modeling β†’ QA Strategy β†’ CI/CD Planning β†’ ADR Generation.

  • Multi-format Export: Output to JSON, YAML, Markdown, or professional SRS documents.

Related MCP server: Phantom MCP

πŸ“‹ Table of Contents

πŸš€ Getting Started

Prerequisites

  • Node.js v18+

  • pnpm (recommended) or npm

Installation

# Clone the repository
git clone https://github.com/vuongdat67/mcp_ssdlc
cd mcp-ssdlc-security-toolkit

# Install dependencies
pnpm install

# Build the project
pnpm build

πŸ’» Configuration

Claude Desktop App

Add to your Claude Desktop configuration:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "ssdlc-toolkit": {
      "command": "node",
      "args": ["path/to/mcp-ssdlc-security-toolkit/dist/index.js"]
    }
  }
}

VS Code

The project includes .vscode/mcp.json for automatic configuration.

Docker

# Build and run with Docker
docker build -t mcp-ssdlc-toolkit .
docker run -it mcp-ssdlc-toolkit

# Or use docker-compose
docker-compose up ssdlc

πŸ› οΈ Available Tools

Tool

Description

list_domains

List all available domain plugins

load_domain

Load a specific domain

detect_domain

Auto-detect domain from description

ba_analyze_requirements

Generate user stories and security requirements

techlead_design

Generate technical design and pseudocode

security_threat_model

Generate STRIDE threat model

qa_design_test_strategy

Generate test strategy

devops_design_cicd

Generate CI/CD pipeline

orchestrate_ssdlc_pipeline

Run complete SSDLC pipeline

🌍 Domains

Built-in Domains

Domain

Compliance

Use Case

healthcare

HIPAA

Patient records, telemedicine

fintech

PCI-DSS

Payments, banking

blockchain

-

Smart contracts, DeFi

secure_comm

GDPR

E2EE messaging

appsec

OWASP

Security tooling

ml_ai

-

ML model security

malware_analysis

-

Malware research

And 10+ more...

Custom Domains

Create custom domains by adding YAML files to domains/custom/:

# domains/custom/ecommerce/domain.yaml
name: "ecommerce"
keywords: ["shop", "cart", "checkout"]
stakeholders:
  - name: "Shopper"
    type: "end_user"
sensitiveData:
  - type: "Payment Data"
    level: "critical"

🐳 Docker

# Development mode
docker-compose up ssdlc-dev

# Production mode
docker-compose up ssdlc

# Run tests
docker-compose run test

πŸ“š Documentation

Full documentation available in the docs/ directory:

🀝 Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

# Run tests
pnpm test

# Run with coverage
pnpm test:coverage

# Lint
pnpm lint

πŸ—ΊοΈ Roadmap

See ROADMAP.md for planned features:

  • v2.1: AI Integration, Interactive CLI, Domain Marketplace

  • v2.5: Real-time Collaboration, Version Control, Third-party Integrations

  • v3.0: Visual Domain Designer, SBOM, Threat Intelligence Feeds

πŸ› οΈ Tech Stack

Feature

Supported Options

Pseudocode Language

Python, TypeScript, Java, Go, C#, C++, Rust

Cloud Target

Kubernetes, AWS, Azure, GCP, Docker

Repo Platform

GitHub, GitLab, Bitbucket

Export Formats

JSON, YAML, Markdown, SRS

πŸ€– Orchestration Example

Ask your AI assistant:

"Design a secure E-wallet system for fintech. Use TypeScript and deploy to AWS. Run the full SSDLC pipeline."

The agent will call orchestrate_ssdlc_pipeline and generate:

  • User stories and security requirements

  • Technical design with pseudocode

  • STRIDE threat model

  • Test strategy

  • CI/CD pipeline

  • Architecture Decision Records (ADRs)

  • Project plan with cost estimation

πŸ“„ License

This project is licensed under the MIT License - see the LICENSE file for details.


Made with ❀️ by the MCP SSDLC team

Available Tools

17 tools
analyze_code_securityC

Analyze code for security issues and vulnerabilities

Inputs: code (required), language (required), domain.

ba_analyze_requirementsC

Generate user stories, security requirements, and abuse cases

Inputs: business_goals (required), project_description (required), domain_name.

detect_domainC

Auto-detect domain from project description

Inputs: project_description (required).

devops_design_cicdC

Generate CI/CD pipeline with security gates

Inputs: tech_stack, project_name, deployment_target, repository_platform.

get_coding_guidelinesC

Get coding guidelines and security rules for a domain

Inputs: domain (required), language (required).

get_last_known_goodC

Get last known good configuration that worked

Inputs: workspace_root (required).

get_secure_templateC

Get a secure code template for a feature type

Inputs: language (required), feature_type (required), domain.

list_domainsB

List all available domain plugins

Inputs: no named parameters.

load_domainC

Load a specific domain plugin

Inputs: domain_name (required).

orchestrate_ssdlc_pipelineC

Run complete SSDLC pipeline from project description

Inputs: tech_stack (required), business_goals (required), project_description (required), target_language, +2 more.

parse_error_logC

Parse error log to extract issues and suggestions

Inputs: log_content (required), log_type.

qa_design_test_strategyC

Generate test cases from features and threats

Inputs: threats, features, compliance_requirements.

run_diagnostic_playbookC

Run a diagnostic playbook to check/fix environment issues

Inputs: playbook (required), workspace_root (required).

run_environment_diagnosticsC

Run diagnostics to check development environment (Node, Git, build tools)

Inputs: workspace_root (required).

security_threat_modelC

Generate STRIDE threat model from modules

Inputs: modules, domain_name, project_name.

techlead_designC

Generate feature checklist, flows, modules, pseudocode, architecture diagram

Inputs: project_name, user_stories, export_format, target_language, +1 more.

workspace_snapshotA

Generate a snapshot of the workspace structure (file tree with .gitignore filtering)

Inputs: root_path (required), max_depth.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    B3/5.0

    Scored across 17 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes, but there is minor overlap between run_diagnostic_playbook and run_environment_diagnostics, and between get_coding_guidelines and get_secure_template. Descriptions are clear enough to differentiate.

    Naming Consistency4/5

    The majority of tools follow a consistent verb_noun pattern (e.g., analyze_code_security, list_domains). However, two tools (security_threat_model, workspace_snapshot) deviate by omitting a verb, creating a minor inconsistency.

    Tool Count5/5

    With 17 tools, the server is well-scoped for a security toolkit covering requirements, design, threat modeling, code analysis, CI/CD, testing, diagnostics, and domain management. Each tool earns its place.

    Completeness4/5

    The toolset covers major SSDLC phases (requirements, design, implementation guidance, analysis, testing, CI/CD). Minor gaps exist, such as lack of deployment security scanning or compliance checks, but core workflows are supported.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Integrates SAST, DAST, IAST, and SCA security testing tools for AI-powered DevSecOps automation, enabling comprehensive security scanning and reporting through natural language interfaces.
      17
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables authorized compliance verification and security auditing through natural language, bridging AI assistants with industry-standard security tools for enterprise audits.
      24
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI-powered security scanning of codebases through conversational analysis, allowing users to assess, threat model, code review, DAST test, and generate security reports using natural language with Claude.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Integrates authoritative security compliance frameworks (ISO 27001, NIST 800-53, OWASP ASVS, NIST SSDF) into AI-assisted development, offering control lookups, cross-framework mappings, build-time guardrails, and automated audit evidence generation.
      244 npm
      3
      MIT