CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Public registry of code-knowledge graphs for AI agents. Awesome-list 2.0: pointers to schema-validated content, not just links.

Agentic-MCP, Progressive MCP client with three-layer lazy loading. Validates AgentSkills.io pattern for efficient token usage. Use MCP without pre-install & wasting full-loading

Tool-to-Agent Protocol: tools can be smart without embedded LLM calls.