by szczyglis-dev · MCP Server · ★ 2.0k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Flagged: installs a cron job, sudo usage. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 1,978 |
| Forks | 351 |
| Language | Python |
| Category | MCP Server |
| Quality Score | 65/100 |
| Open Issues | 64 |
| Last Updated | 2026-10-06 |
| Created | 2023-04-09 |
| Platforms | browser, claude-code, gemini, mcp, python |
| Est. Tokens | ~25k |
PyGPT - Desktop AI Assistant Release: 2.7.12 Python: =3.10, Official website: https://pygpt.net | Documentation: https://pygpt.readthedocs.io Discord: https://pygpt.net/discord PyPi: https://pypi.org/project/pygpt-net Compiled version for Linux () and Windows 10/11 () 64-bit: https://pygpt.net/#download ❤️ Donate: https://www.buymeacoffee.com/szczyglis | https://github.com/sponsors/szczyglis-dev...
These tools work well together with py-gpt for enhanced workflows:
Looking for a py-gpt alternative? If you're comparing py-gpt with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
The pretty much "official" DSPy framework for Typescript
Production-ready AI chat. Start here and make it your own.
ARGO is an open-source AI Agent platform that brings Local Manus to your desktop. With one-click model downloa
Your personal AI assistant, running on your own computer. Long-running tasks, real memory, proactive help, voi
Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gem
🐬DeepChat - A smart assistant that connects powerful AI to your personal world
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: