Generate Tech Stack
This server scans a project directory to detect its tech stack and can either generate a visual HTML report or return the findings as structured JSON.
Generate a visual HTML report (
generate_tech_stack): Produces a self-containedTECH_STACK.htmlfile featuring a stat row (total tools, categories, AI backends, data stores), a layered architecture diagram, a horizontal bar chart, and colour-coded tool cards. Optionally auto-opens in your default browser. Output path and project directory are configurable.Return a structured JSON summary (
list_tech_stack): Scans the project and returns the tech stack as structured JSON without writing any file — ideal for programmatic or downstream use.Detects a wide range of technologies: Languages (Python, Go, Rust, TypeScript, Java, PHP...), frameworks (FastAPI, Django, Express, Next.js...), databases (PostgreSQL, Redis, MongoDB, SQLite...), AI/ML SDKs, testing, observability, security, and infrastructure (Docker, Kubernetes, CI/CD, GitHub Actions, GitLab CI).
Zero configuration required: All inputs are optional and default to the current working directory. Works with Claude Desktop, VS Code, Cursor, Zed, and Continue.
Provides a GitHub Copilot Extension that allows users to generate tech stack reports by invoking /generate-tech-stack in Copilot Chat.
generate-tech-stack
Scan any project and generate a visual TECH_STACK.html page — light/dark theme, auto-adapting, zero config.
Works as a Claude Code skill, MCP server, or GitHub Copilot Extension.
Live demo → — generated from fastapi/full-stack-fastapi-template, unmodified.

(real CLI output, unscripted — static screenshot if you'd rather not autoplay)
What it produces
Every generated page contains:
Section | Description |
Stat row | Total tools · Categories · AI Backends · Data Stores |
Architecture diagram | Layered flow diagram (Consumer → API → AI/NLP → Data/Obs/Frontend) |
Bar chart | Horizontal bars per category, colour-matched |
Tool cards | One card per category; each tool shows a dot, name, description, and badge |
Badge legend | Explains |
Footer | Project name · tool count · generation date |
Guided tour | Spotlight walkthrough of every section, shown automatically the first time a report is opened; replay anytime with the |
Theme toggle | Sun/moon button next to the tour button switches between dark and light mode |
Related MCP server: mcp-repo-graph
Repository layout
~/.claude/skills/generate-tech-stack/
├── SKILL.md ← Claude Code skill definition
├── INSTALL.md ← detailed per-platform installation guide
├── README.md ← this file
├── scripts/
│ └── analyze.py ← core scanner + HTML renderer (no dependencies)
├── mcp/
│ ├── server.py ← MCP stdio server (pip install mcp)
│ └── requirements.txt
└── copilot/
├── index.js ← GitHub Copilot Extension (Express)
├── package.json
└── openai_function.json ← OpenAI / Antigravity function definitionUsage
pip (CLI + MCP server)
pip install generate-tech-stack-mcp
generate-tech-stack . TECH_STACK.html # CLI: scan and write the report
generate-tech-stack-mcp # stdio MCP serverWith pip installed, any MCP host config reduces to:
{
"mcpServers": {
"generate-tech-stack": { "command": "generate-tech-stack-mcp" }
}
}Claude Code
/generate-tech-stackRun it from any project directory. The skill calls scripts/analyze.py and opens the result in your browser.
MCP (Claude Desktop, VS Code, Cursor, Zed, Windsurf, Continue)
pip install mcpAdd to your host's MCP config (replace the path with your actual home directory):
{
"mcpServers": {
"generate-tech-stack": {
"command": "python3",
"args": ["/home/<you>/.claude/skills/generate-tech-stack/mcp/server.py"]
}
}
}Then ask: generate my tech stack or /generate-tech-stack.
MCP tools exposed:
generate_tech_stack— scans a project, writesTECH_STACK.html, opens in browserlist_tech_stack— returns a JSON summary, no file written
GitHub Copilot Extension
cd copilot
npm install
npm start # listens on port 3000
ngrok http 3000 # expose for GitHub to reachRegister a GitHub App with Copilot Extension enabled, set the Agent URL to https://your-url/agent, and install it on your account. Then in Copilot Chat:
@generate-tech-stack /generate-tech-stack
@generate-tech-stack /generate-tech-stack /path/to/projectCommand line (standalone)
python3 ~/.claude/skills/generate-tech-stack/scripts/analyze.py /path/to/project
# output: /path/to/project/TECH_STACK.html
# custom output path:
python3 scripts/analyze.py . ~/Desktop/TECH_STACK.htmlanalyze.py has no third-party dependencies — just Python 3.8+.
What gets detected
Source file | Detected tools |
| Python packages (web, DB, AI, testing, observability, security…) |
| Node / npm packages (frameworks, frontend, DB drivers, tooling) |
| Go language |
| Rust language |
| Java / Kotlin |
| Ruby |
| PHP |
| Optional/dynamic SDKs via |
| PostgreSQL, Redis, MongoDB, SQLite connection strings |
| Docker |
| Docker Compose |
| GitHub Actions |
| GitLab CI |
| Alembic migrations |
| Reverse proxy |
| TypeScript |
Detected categories
Category | Colour | Examples |
Language & Runtime | Green | Python, Go, Rust, TypeScript |
Web / API Framework | Purple | FastAPI, Express, Django, Next.js |
Database / Storage | Green | SQLAlchemy, Prisma, Redis, ChromaDB |
AI SDKs | Blue | OpenAI, Anthropic, LangChain, GuardrailsAI, NVIDIA NeMo, Presidio |
NLP / ML | Teal | spaCy, Transformers, Sentence Transformers |
Observability | Teal | Prometheus, OpenTelemetry, Sentry, Loguru |
Testing | Yellow | pytest, Jest, Cypress, Playwright |
Security / Auth | Rose | PyJWT, bcrypt, Authlib, Helmet |
Infrastructure / Deploy | Orange | Docker, Kubernetes, Celery, Boto3 |
Frontend / Dashboard | Gray | React, Vue, Tailwind, Recharts |
Messaging / Comms | Blue | Kafka, RabbitMQ, Socket.io |
Dev Tools | Gray | ESLint, Prettier, Vite, TypeScript |
Design
Dark by default with a light-mode toggle (top-right corner, no persistence — resets to dark on reload). Fonts: IBM Plex Sans (body) + JetBrains Mono (code/badges), loaded from Google Fonts. Vanilla JS powers the guided tour and theme toggle only — everything else is plain HTML + CSS. Self-contained single file, opens in any browser offline.
See also
INSTALL.md — per-platform setup instructions
SKILL.md — Claude Code skill specification
Available Tools
2 toolsgenerate_tech_stackA
Scan a project directory and generate a TECH_STACK.html visual page. Includes a stat row, layered architecture diagram, bar chart summary, and colour-coded tool cards. Detects languages, frameworks, databases, AI SDKs, testing, observability, security, and infrastructure tools.
Inputs: output_file, project_dir, open_browser.
list_tech_stackA
Scan a project and return the tech stack as structured JSON (no HTML file written). Good for programmatic use.
Inputs: project_dir.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one generates a visual HTML report, the other returns structured JSON for programmatic use. No overlap in functionality.
Both tools use 'tech_stack' noun consistently, but the verbs differ ('generate' vs 'list') which is a minor inconsistency. Mostly follows verb_noun pattern.
Two tools are appropriate for the narrow domain of detecting and outputting a tech stack. The pair covers the essential use cases without unnecessary bloat.
The tools cover both visual and data-driven outputs, which are the primary needs for tech stack generation. No obvious gaps for the stated purpose.
Maintenance
Related MCP Connectors
AI-powered codebase analysis — call graphs, security, dead code, complexity. 150+ tools.
Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.
Codebase intelligence for AI agents — dead code, blast radius, ownership.
Codebase intelligence for AI coding agents: graph, git history, docs, decisions, code health.
Related MCP Servers
- AlicenseAqualityCmaintenanceArchitectural memory layer for AI coding. Automatically extracts decisions, detects security gaps, and analyzes git history from your codebase in one command.328 npm2MIT
- AlicenseAqualityBmaintenanceStructural graph map of any codebase. Scans entities, relationships, and feature flows across 13 languages so LLMs navigate by structure instead of reading everything.6140 PyPI50MIT
- AlicenseAqualityDmaintenanceAnalyzes codebases from local directories, GitHub, and Azure DevOps, providing intelligent context to AI coding assistants through repository structure, critical files, and semantic maps.144MIT
- AlicenseBqualityDmaintenanceTransforms codebases into structural knowledge graphs for AI agents and developers, providing precise architectural awareness and dependency mapping.1530MIT