What skills format does it expect?
Each skill is a folder containing a `SKILL.md` file.
@back1ply
Basic information
MCP server to expose Claude Code Skills to AI agents
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"agent-skill-loader": {
"command": "npx",
"args": [
"-y",
"agent-skill-loader"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
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.
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.
Each skill is a folder containing a `SKILL.md` file.
Use the `manage_search_paths` tool at runtime with `operation="add"` and the path.
Yes, use `install_skill(skill_name)` which copies the folder to `.agent/skills/<name>` within the current workspace.
Node.js >= 18.
It scans `%USERPROFILE%\.claude\plugins\cache` and a `skill-paths.json` file in the project root.

scvd.store is an evidence observatory for agentic commerce. Independent signed observation of what other people's endpoints, artifacts and payments actually did among other things. USDC on Base, Arbitrum One, World Chain
BERGHAIN MCP server — sovereign AI stress-testing mcp / ai / multi-agent / adversarial / stress-test / claude

A record of what an agent did that the agent cannot quietly rewrite, and a way for anyone to check.
TruVerifAI's Panel Review is the guardian agent for AI's highest-stakes coding decisions: four frontier models argue over an AI coding agent's riskiest designs, diffs, and commits before they execute, with local review g

Anyreach is a platform for building AI agents that handle real customer conversations across channels — phone calls, web voice and chat, and email — for sales, support, scheduling, and surveys. You configure an agent onc
Comments