io.github.back1ply/agent-skill-loader MCP Server
io.github.back1ply/agent-skill-loader
Dynamically load Claude Code skills into AI agents as slash commands and tools without copying files.
What this kind of tool is for
- Automate a build, test, or deployment step you repeat by hand.
- Review or refactor code in an existing repository without leaving your agent.
- Bridge an internal service or CLI into the agent toolset.
How to compare servers like this
- Scope of control:
- Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
- Environment fit:
- Match the runtime it expects (Node, Python, a container) to what you actually run.
- Maintenance signal:
- Check the last-commit date — dev tooling that lags upstream breaks first.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the io.github.back1ply/agent-skill-loader MCP server?
Agent Skill Loader is an MCP server that bridges Claude Code Skills libraries with dynamic AI agents like Claude Desktop and Cursor. It exposes skills as MCP Prompts (slash commands) and MCP Tools, auto-discovering them from configured directories with live file-watching updates.
Agent Skill Loader lets you maintain a centralized library of Claude Code skills and inject them into AI agents on-demand. Skills appear as slash commands in supported clients and can be queried programmatically. The server watches skill directories for changes, automatically notifying clients when skills are added or removed, eliminating the need to manually copy files or restart.
How to install io.github.back1ply/agent-skill-loader
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"agent-skill-loader": {
"command": "npx",
"args": [
"-y",
"agent-skill-loader"
]
}
}
}Tools & capabilities
Tools this server exposes to the agent.
list_skills— Returns a JSON list of available skills with optional query filtering by name or description.read_skill— Fetches and returns the markdown instructions for a specified skill.install_skill— Copies a skill folder permanently to the project's .agent/skills directory.manage_search_paths— Add, remove, or list skill search directories at runtime.debug_info— Returns diagnostic information including search paths, path status, and warnings.
Use cases
- Inject expert-knowledge skills (e.g., DAX measures, SQL optimization) into Claude conversations via slash commands
- Maintain a shared skill library across multiple projects without duplicating files
- Discover and load specialized skills dynamically based on agent needs
- Troubleshoot skill discovery and path configuration issues
- Extend AI agent capabilities with custom, reusable skill sets
io.github.back1ply/agent-skill-loader MCP server FAQ
It's an MCP server that makes Claude Code skills available to AI agents as both slash commands (MCP Prompts) and programmatic tools, with automatic discovery and live updates.
Yes, Agent Skill Loader is open-source under the MIT license.
Install via npm (`npm install -g agent-skill-loader`) and register it in your `.mcp.json` config file with the command `agent-skill-loader`.
No, Agent Skill Loader does not require authentication. It scans local directories configured via environment variables or a `skill-paths.json` file.
Skills must be folders containing a `SKILL.md` file with markdown instructions. The server auto-discovers them from configured directories.
Yes, use the `manage_search_paths` tool to add or remove skill directories at runtime without editing config files or restarting.
README (reference)
Source of truth, from the repository.
Agent Skill Loader 🧠
Agent Skill Loader is a Model Context Protocol (MCP) server that acts as a bridge between your static Claude Code Skills library and dynamic AI agents (like Claude Desktop, Cursor, or any MCP client).
It exposes skills both as MCP Prompts (slash commands, zero tool calls needed) and as MCP Tools (for programmatic use). Skills are auto-discovered from configured directories and stay live — add a new SKILL.md and the client is notified automatically.
🚀 Features
- MCP Prompts: Skills appear as slash commands in clients. No tool call needed to inject them.
- Live updates:
listChangednotification fires when skills are added or removed (via file watcher). - Discovery:
list_skills— scans configured skill directories, with optional search filter. - Dynamic Learning:
read_skill— fetches theSKILL.mdcontent. - Persistence:
install_skill— copies a skill permanently to your project. - Configuration:
manage_search_paths— add/remove skill directories at runtime. - Troubleshooting:
debug_info— diagnose configuration and path issues.
🛠️ Setup
Prerequisites
- Node.js >= 18
Option A: Install from npm (Recommended)
npm install -g agent-skill-loader
Then register in .mcp.json:
"agent-skill-loader": {
"command": "agent-skill-loader"
}
Option B: Build from Source
git clone https://github.com/back1ply/agent-skill-loader.git
cd agent-skill-loader
npm install
npm run build
Then register in .mcp.json:
"agent-skill-loader": {
"command": "node",
"args": ["<path-to-repo>/build/index.js"]
}
📂 Configuration
The server automatically detects its workspace and aggregates skill paths from:
- Default:
%USERPROFILE%\.claude\plugins\cache(Standard location) - Dynamic Config:
skill-paths.json(Located in the project root)
Environment Variables
| Variable | Description |
|---|---|
MCP_SKILL_PATHS | JSON array or semicolon/comma-separated list of additional skill paths |
MCP_WORKSPACE_ROOT | Override auto-detected workspace root |
MCP_NO_WATCH | Set to 1 to disable the file watcher (useful in CI) |
Dynamic Path Management
You do not need to manually edit config files. Use the tool to manage paths at runtime:
- Add:
manage_search_paths(operation="add", path="F:\\My\\Deep\\Skills") - Remove:
manage_search_paths(operation="remove", path="...") - List:
manage_search_paths(operation="list")creates/updatesskill-paths.json.
🤖 Usage
MCP Prompts (Slash Commands)
If your client supports MCP Prompts (Claude Desktop, Cursor, etc.), skills appear automatically as slash commands. Select a skill from the slash command menu to inject its content directly — no tool calls needed.
Tools
The agent has access to five tools:
list_skills(query?): Returns a JSON list of available skills. Optionalqueryfilters by name/description substring (case-insensitive).read_skill(skill_name): Returns the markdown instructions for a skill.install_skill(skill_name, target_path?): Copies the skill folder to.agent/skills/<name>. For security,target_pathmust be within the current workspace.manage_search_paths(operation, path?): Add, remove, or list skill search paths.debug_info(): Returns diagnostic information (paths, status, warnings).
Example Agent Prompt
"I need to write a DAX measure but I'm not sure about the best practices."
The agent will automatically call list_skills, find writing-dax-measures, call read_skill, and answer with expert knowledge. Or the user can invoke the skill directly as a slash command.
🔧 Troubleshooting
If skills aren't being discovered, use debug_info() to see:
- search_paths: Which directories are being scanned
- path_status: Whether each path exists and is readable
- warnings: Any errors encountered during scanning (permission denied, empty files, etc.)
Example output:
{
"workspace_root": "C:/projects/agent-skill-loader",
"search_paths": {
"base": ["C:/Users/pc/.claude/plugins/cache"],
"dynamic": ["F:/My/Skills"],
"effective": ["C:/Users/pc/.claude/plugins/cache", "F:/My/Skills"]
},
"path_status": [
{ "path": "C:/Users/pc/.claude/plugins/cache", "exists": true, "readable": true },
{ "path": "F:/My/Skills", "exists": false, "readable": false }
],
"skills_found": 12,
"warnings": [
{ "path": "F:/My/Skills", "reason": "Directory does not exist" }
]
}
📦 Project Structure
src/index.ts: Main server logic (tools + prompts + watcher).src/utils.ts: Skill scanning, description extraction, prompt helpers, debounce.build/: Compiled JavaScript output.package.json: Dependencies (@modelcontextprotocol/sdk,chokidar,zod).
🤝 Contributing
To add new skills, add a folder with a SKILL.md file to one of the watched directories. The server picks them up automatically and sends a listChanged notification — no restart required.
Related MCP servers

Beget Hosting
Beget hosting: sites, domains, DNS, MySQL, FTP, cron, backups, mail — 73 tools

io.github.baixianger/camoufox-mcp
Anti-detection browser automation with Camoufox - stealth Firefox for web scraping

io.github.bamchi/scrapi
Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.

Backblaze B2 MCP Server
Official Backblaze B2 MCP server for cloud storage buckets, files, keys, Object Lock, and S3-compatible operations.

Backlinkswinkel
Search Dutch sites in the Backlinkswinkel catalogue, order backlinks after confirmation, track them.
