Flagged: environment access. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by agentscope-ai · MCP Server · ★ 32.2k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is agentscope safe to install? View the security audit →
中文主页 FAQ <img src="https://img.shields.io/badge/Docs-English%7C%
| Stars | 32,170 |
| Forks | 3,537 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 69.9509523227333/100 |
| Open Issues | 417 |
| Last Updated | 2026-09-22 |
| Created | 2024-01-12 |
| Platforms | mcp, python |
| Est. Tokens | ~18k |
These tools work well together with agentscope for enhanced workflows:
Looking for a agentscope alternative? If you're comparing agentscope 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.
AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature,
CowAgent是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、拥有长期记忆并不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页
A generative speech model for daily dialogue.
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for w
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
Pocket Flow: Codebase to Tutorial
Explore other popular mcp server tools:
agentscope is Build and run agents you can see, understand and trust.. It is categorized as a MCP Server with 32.2k GitHub stars.
agentscope is primarily written in Python. It covers topics such as agent, chatbot, large-language-models.
You can find installation instructions and usage details in the agentscope GitHub repository at github.com/agentscope-ai/agentscope. The project has 32.2k stars and 3537 forks, indicating an active community.
agentscope is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to agentscope on Agent Skills Hub include AstrBot, chatgpt-on-wechat, ChatTTS. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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: