by weidu12123 · MCP Server · ★ 220
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
梨园 Liyuan — 以 rp agent为主体的ai角色扮演应用
| Stars | 220 |
| Forks | 25 |
| Language | TypeScript |
| Category | MCP Server |
| Quality Score | 45.2255971995808/100 |
| Last Updated | 2026-09-15 |
| Created | 2026-07-12 |
| Platforms | browser, mcp, node |
| Est. Tokens | ~13k |
These tools work well together with Liyuan for enhanced workflows:
Looking for a Liyuan alternative? If you're comparing Liyuan 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.
Self-hosted AI roleplay chat platform you run on your PC or personal server, forked from Risuai
Protocol-agnostic CesiumJS AI control runtime for MCP, WebMCP, function calling, and browser agents.
Agent harness and tookit for building AI agents and agentic applications. CLI and SDKs included
Aser is a lightweight, self-assembling AI Agent frame.
One secure endpoint for every MCP server. Deploy anywhere.
📜 An MCP server for conversation history search and retrieval in Claude Code
Explore other popular mcp server tools:
Liyuan is 梨园 Liyuan — 以 rp agent为主体的ai角色扮演应用. It is categorized as a MCP Server with 220 GitHub stars.
Liyuan is primarily written in TypeScript. It covers topics such as agent, ai, ai-agent.
You can find installation instructions and usage details in the Liyuan GitHub repository at github.com/weidu12123/Liyuan. The project has 220 stars and 25 forks, indicating an active community.
The top alternatives to Liyuan on Agent Skills Hub include PocketRisu, cesium-mcp, dexto. 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: