What languages does Skylos support?
Python, TypeScript, and Go.

@duriantaco
Basic information
Dead code detection, security scanning, and code quality analysis for Python, TypeScript, and Go. 98% recall with 3x fewer false positives than Vulture. 5 tools: analyze, security_scan, quality_check, secrets_scan, remediate. AI-powered auto-fix agent.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"skylos": {
"command": "python3",
"args": [
"-m",
"skylos_mcp.server"
]
}
}
}Dead code detection (unused functions, imports, classes, variables)
Security vulnerability scan (`--danger` equivalent)
Code quality and complexity analysis (`--quality` equivalent)
Hardcoded secrets detection (`--secrets` equivalent)
End-to-end: scan, generate LLM fixes, validate with tests
Skylos is a privacy-first SAST tool for Python, TypeScript, and Go that detects dead code, security vulnerabilities (SQLi, SSRF, secrets), and code quality issues with high precision. It uses a hybrid engine (AST + optional local/cloud LLM) and supports agentic AI fixes, making it suitable for developers and security teams who want fast, accurate static analysis that respects code privacy.
Install via pip (pip install skylos) and run commands like skylos . to scan for dead code, skylos . --secrets --danger --quality for security and quality audits, or skylos agent analyze . --model gpt-4.1 for AI-powered analysis. For CI/CD, run skylos cicd init to generate a GitHub Actions workflow in 30 seconds.
Python, TypeScript, and Go.
No. Skylos is designed to be 100% local and privacy-first. When using the optional cloud LLM analysis, you can choose to send selected files, but local LLMs (Ollama, LM Studio) keep everything on your machine.
In benchmarks on 9 popular Python repos, Skylos achieved 98.1% recall (51/52) vs Vulture’s 84.6% (44/52), with only 220 false positives compared to Vulture’s 644. Skylos is also framework-aware (FastAPI, Django, pytest) and supports security scanning, TypeScript, and Go.
Not for local scan modes. For AI-powered analysis you can use a local LLM (no API key) or provide a key for cloud models like GPT‑4.1 or Claude.
Yes. Use `skylos cicd init` to generate a GitHub Actions workflow in 30 seconds. It automatically adds dead code detection, security scanning, and quality gates on every PR.

Most MCP servers hand your agent documentation. This one hands it a renderer. Write a single React Native codebase that ships native AR to phones and VR to headsets, then let your agent validate every prop, check each pl

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Comments