Agent Skill Loader
@back1ply
关于 Agent Skill Loader
MCP server to expose Claude Code Skills to AI agents
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"agent-skill-loader": {
"command": "npx",
"args": [
"-y",
"agent-skill-loader"
]
}
}
}工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is Agent Skill Loader?
Agent Skill Loader is a Model Context Protocol (MCP) server that bridges a static Claude Code Skills library with dynamic AI agents (like Antigravity, Claude Desktop, or Cursor). It allows agents to learn skills on demand without requiring manual file copying into every project.
How to use Agent Skill Loader?
Install globally via npm (npm install -g agent-skill-loader) and register the server in .mcp.json. Alternatively, build from source. After setup, agents have access to five tools: list_skills, read_skill, install_skill, manage_search_paths, and debug_info.
Key features of Agent Skill Loader
- Scans configured skill directories for discovery.
- Fetches SKILL.md content for agents to read.
- Copies skill permanently to project if needed.
- Adds or removes skill directories at runtime.
- Diagnoses configuration and path issues.
Use cases of Agent Skill Loader
- An agent automatically finds and reads a skill for writing DAX measures.
- Developers maintain a central skills library used across projects.
- Dynamic learning without manually copying skill files into each project.
- Troubleshoot skill discovery using the debug_info tool.
FAQ from Agent Skill Loader
What skills format does it expect?
Each skill is a folder containing a SKILL.md file.
How do I add custom skill directories?
Use the manage_search_paths tool at runtime with operation="add" and the path.
Can I install a skill permanently into a project?
Yes, use install_skill(skill_name) which copies the folder to .agent/skills/<name> within the current workspace.
What runtime does it require?
Node.js >= 18.
Where does the server look for skills by default?
It scans %USERPROFILE%\.claude\plugins\cache and a skill-paths.json file in the project root.
AI 与智能体 分类下的更多 MCP 服务器
Sequential Thinking Multi-Agent System (MAS)
FradSerAn advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.
Open Multi-Agent Canvas
CopilotKitThe open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research
meGPT - upload an author's content into an LLM
adriancoCode to process many kinds of content by an author into an MCP server
MCP Client for Ollama (ollmcp)
joniglHarness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre
Model Context Protocol for Unreal Engine
chongdashuEnable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).
评论