agent_skills_directory
Verified Safeby dmgrok
Overview
Provides a centralized, automatically-updated catalog of AI agent skills from multiple providers, consumable by MCP servers, AI agents, and developer tools.
Installation
python scripts/aggregate.pyEnvironment Variables
- GITHUB_TOKEN
Security Notes
The primary `aggregate.py` script uses `yaml.safe_load` for parsing YAML frontmatter, which is a secure practice. It retrieves the GitHub token from environment variables, preventing hardcoding. Network requests are made to GitHub APIs, which is expected. The use of `subprocess.run` to call `npx @toon-format/cli` carries a moderate theoretical risk if the `toon-format/cli` itself has vulnerabilities or if the input to it were untrusted. However, in this context, it processes locally generated content (`catalog.json`), mitigating direct input-based injection risks. No `eval` or obvious malicious patterns were detected.
Similar Servers
klavis
Develop and deploy AI agents that interact with a wide array of web services (e.g., Gmail, YouTube, LinkedIn, Supabase, Salesforce, Kubernetes) through a standardized Model Context Protocol (MCP), often orchestrated by an intelligent routing layer like Strata.
MCPJungle
MCPJungle is a self-hosted gateway for registering, managing, and securely proxying Model Context Protocol (MCP) servers and their AI agent tools from a central location.
skillz
Acts as an MCP server to expose Claude-style skills and their resources as callable tools for AI agents.
mcp-servers
Manage files and objects in cloud storage services like Google Cloud Storage, with capabilities for saving, retrieving, searching, and deleting files.