Dynamically loads Claude Code skills into AI agents as MCP prompts and tools through automatic directory scanning.
Also known as back1ply/agent-skill-loader
- Stars
- 15
- Tools
- 5
- Downloads, 30 days
- —
- Latest version
- 1.2.1
- Last commit
- Nov 10, 2026
- License
- MIT
What is agent-skill-loader MCP?
agent-skill-loader is an MCP server. Dynamically loads Claude Code skills into AI agents as MCP prompts and tools through automatic directory scanning. It exposes 5 tools, such as list_skills, read_skill, install_skill.
Summary generated from the project's README
About agent-skill-loader MCP server
Connecting your Claude Code skills library to dynamic AI agents like Claude Desktop or Cursor is what this server enables. It acts as a bridge that transforms static markdown files into active MCP prompts and tools. By scanning configured directories for SKILL.md files, it allows agents to discover and use specialized knowledge without manual configuration changes.
Developers use this server locally by installing it via npm and registering it in an MCP configuration file. It supports automatic discovery from default plugin cache locations or custom paths defined in a skill-paths.json file. The server uses a file watcher to provide live updates, meaning new skills are immediately available to the client via listChanged notifications without needing a restart.
Users interact with the system through slash commands for quick prompt injection or via specific tools. The toolset includes list_skills for searching available expertise, read_skill to fetch markdown instructions, and install_skill to copy a skill into a project workspace. It also provides manage_search_paths to update directory locations at runtime and debug_info to troubleshoot path permissions or scanning errors.
What you can do with it
- 1Injecting specialized knowledge via slash commandsA developer can use slash commands in a compatible client to immediately inject a skill's instructions into the conversation.
- 2Managing skill directories at runtimeYou can add or remove directories containing skill files without manually editing configuration files.
- 3Permanently installing skills into a projectA developer can copy a specific skill from a central library directly into their current project workspace.
Written from the project's README. Every use case is checked against a quote from it.
How to install agent-skill-loader MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall agent-skill-loader MCP in Claude Code
$ claude mcp add agent-skill-loader -- npx -y agent-skill-loaderInstall agent-skill-loader MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agent-skill-loader": {
"command": "npx",
"args": [
"-y",
"agent-skill-loader"
]
}
}
}Install agent-skill-loader MCP in VS Code
.vscode/mcp.json
{
"servers": {
"agent-skill-loader": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agent-skill-loader"
]
}
}
}Install agent-skill-loader MCP in VS Code CLI
$ code --add-mcp '{"name":"agent-skill-loader","type":"stdio","command":"npx","args":["-y","agent-skill-loader"]}'Install agent-skill-loader MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"agent-skill-loader": {
"command": "npx",
"args": [
"-y",
"agent-skill-loader"
]
}
}
}Install agent-skill-loader MCP in Codex
$ codex mcp add agent-skill-loader -- npx -y agent-skill-loaderInstall agent-skill-loader MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.agent-skill-loader] command = "npx" args = ["-y", "agent-skill-loader"]
Install agent-skill-loader MCP in Gemini CLI
$ gemini mcp add -s user agent-skill-loader npx -- -y agent-skill-loaderInstall agent-skill-loader MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agent-skill-loader": {
"command": "npx",
"args": [
"-y",
"agent-skill-loader"
]
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for agent-skill-loader 1.2.1 in an isolated container with no network and no keys. It answered and listed 5 tools.
agent-skill-loader MCP tools 5
Read from the server with tools/listlist_skillsRead-onlyReturns a JSON list of all available skills with their names, descriptions, and source directories. Use this to discover what skills are available before reading or installing them.
read_skillRead-onlyFetches and returns the full SKILL.md content for a specific skill. The content includes instructions and context that can be used to learn the skill's capabilities.
install_skillCopies an entire skill directory (including SKILL.md and any supporting files) to the target workspace. By default, installs to .agent/skills/<skill_name> in the current working directory.
manage_search_pathsActionAdd, remove, or list dynamic skill search paths without restarting the server. Persists to skill-paths.json in the workspace root.
debug_infoRead-onlyReturns diagnostic information about server configuration, search paths, and any warnings from the last scan. Use this when skills aren't being found or to verify configuration.
| list_skills | Returns a JSON list of all available skills with their names, descriptions, and source directories. Use this to discover what skills are available before reading or installing them. | Read-only |
| read_skill | Fetches and returns the full SKILL.md content for a specific skill. The content includes instructions and context that can be used to learn the skill's capabilities. | Read-only |
| install_skill | Copies an entire skill directory (including SKILL.md and any supporting files) to the target workspace. By default, installs to .agent/skills/<skill_name> in the current working directory. | |
| manage_search_paths | Add, remove, or list dynamic skill search paths without restarting the server. Persists to skill-paths.json in the workspace root. | Action |
| debug_info | Returns diagnostic information about server configuration, search paths, and any warnings from the last scan. Use this when skills aren't being found or to verify configuration. | Read-only |
Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHubAgent 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.
agent-skill-loader MCP questions
How do I add agent-skill-loader MCP to Claude Code?
Run claude mcp add agent-skill-loader -- npx -y agent-skill-loader in your terminal. Add --scope user to make it available in every project.
How do I add agent-skill-loader MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does agent-skill-loader MCP provide?
It exposes 5 tools, including list_skills, read_skill, install_skill, manage_search_paths, debug_info.
How do I add new skills to the server?
You can add a new skill by placing a folder containing a SKILL.md file into one of the configured skill directories.
Can I manage skill directories without editing configuration files manually?
Yes, you can use the manage_search_paths tool to add, remove, or list skill directories at runtime.