Skene
Product-Led Growth (PLG) analysis toolkit that detects tech stacks, plans growth loops and builds the loop iteratively.
What is Skene?
Skene is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to product-led growth (plg) analysis toolkit that detects tech stacks, plans growth loops and builds the loop iteratively.
Product-Led Growth (PLG) analysis toolkit that detects tech stacks, plans growth loops and builds the loop iteratively.
This server falls under the Analytics category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Product-Led Growth (PLG) analysis toolkit that detects tech
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx skeneConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Skene
Skene is a Product-Led Growth (PLG) analysis toolkit and CLI tool written in Go that analyzes codebases and SQL schemas to automatically detect tech stacks, generate user journey maps across seven lifecycle stages, and build iterative growth loops grounded in evidence from the code. It uses a dual-agent analysis approach — one agent reads code, another reads SQL schemas — and produces a YAML bundle with confidence-scored milestones and an interactive web visualization. Product managers, growth engineers, and founders who want AI-assisted PLG strategy derived directly from their codebase will find Skene immediately applicable.
Prerequisites
- A codebase accessible on your local machine to analyze
- An LLM provider API key (supports OpenAI, Anthropic Claude, Google Gemini, or a local model via Ollama/LM Studio)
- curl for running the install script, or pip for the Python CLI
- Optional: exported SQL schema files if you want database-aware journey mapping
Install Skene using the terminal UI installer
The fastest way to get started is the TUI installer script, which guides you through provider selection and authentication.
curl -fsSL https://raw.githubusercontent.com/SkeneTechnologies/skene/main/tui/install.sh | bashAlternatively, install the Python CLI via pip or uvx
Install the skene Python package globally or run it without installation using uvx.
# Run without installing
uvx skene analyse-journey .
# Or install globally
pip install skeneRun the interactive setup wizard
Launch Skene and follow the interactive wizard to select your LLM provider and authenticate. The wizard walks you through every step.
skeneAnalyze your project's user journey
Run the analyse-journey command in your project root. Skene scans your code and optionally your SQL schemas to generate a journey.yaml output bundle.
cd /path/to/your/project
skene analyse-journey .
# With SQL schema files
skene analyse-journey . --schema-dir ./sql-schemas
# Custom output location
skene analyse-journey . -o ./skene-outputReview the generated journey and visualizations
Skene writes a bundle to ./skene-context/journey.yaml with evidence-backed lifecycle stage milestones and an interactive web visualization you can open in a browser.
Skene Examples
Client configuration
Skene is a CLI tool rather than a traditional MCP server. This shows the typical invocation for a project analysis.
{
"note": "Skene is invoked as a CLI tool. Example wrangler for running via npx:",
"mcpServers": {
"skene": {
"command": "npx",
"args": ["skene", "analyse-journey", "."]
}
}
}Prompts to try
CLI commands and scenarios for using Skene's PLG analysis capabilities
- "skene analyse-journey . --schema-dir ./migrations" — analyze codebase with SQL schema context
- "skene analyse-journey . --no-specialize" — keep canonical PLG stage names instead of customized ones
- "skene analyse-journey . -o ./growth-analysis" — output results to a specific directory
- "Review the generated skene-context/journey.yaml and identify which lifecycle stage has the lowest confidence score."Troubleshooting Skene
Skene fails to authenticate with the LLM provider
Re-run 'skene' to enter the interactive wizard again and re-enter your API key. For Anthropic, ensure your key starts with 'sk-ant-' and has sufficient credits.
Journey generation produces empty or very low-confidence milestones
Include SQL schema files using --schema-dir to give Skene's second analysis agent database context. Also ensure the codebase directory contains actual application code rather than only configuration files.
uvx skene not found or package not found on PyPI
Ensure you are using a recent version of uv ('uv self update') and that the 'skene' package is published and available on PyPI. If the package is unavailable, fall back to the TUI installer script.
Frequently Asked Questions about Skene
What is Skene?
Skene is a Model Context Protocol (MCP) server that product-led growth (plg) analysis toolkit that detects tech stacks, plans growth loops and builds the loop iteratively. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Skene?
Follow the installation instructions on the Skene GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Skene?
Skene works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Skene free to use?
Yes, Skene is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Skene Alternatives — Similar Analytics Servers
Looking for alternatives to Skene? Here are other popular analytics servers you can use with Claude, Cursor, and VS Code.
OpenMetadata
★ 14.0kOpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team collaboration.
Superset
★ 10.9kAn MCP server that provides AI assistants with full access to Apache Superset instances, enabling interaction with dashboards, charts, datasets, databases, and SQL execution capabilities.
Horizon
★ 4.4k📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达
MCP Server Chart
★ 4.1kEnables generation of 25+ types of charts and data visualizations using AntV, including bar charts, line charts, maps, mind maps, and specialized diagrams like fishbone and sankey charts. Supports both statistical charts and geographic visualizations
Muapi CLI
★ 997Official CLI for muapi.ai — generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.
Weather MCP Server
★ 907Weather Data Fetcher MCP server built with Node.js, MCP SDK, and Zod. Provides weather details like temperature and forecast for cities such as Noida and Delhi via a registered tool. Simplifies API integration, enabling structured responses for clien
Browse More Analytics MCP Servers
Explore all analytics servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Skene in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Skene?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.