"Pocket" matching MCP servers:

A small, readable MCP learning project implemented in TypeScript that uses a local JSON notebook to demonstrate core MCP features such as tools, resources, prompts, sampling, and notifications.

Enables AI assistants to rapidly gather and synthesize structural, chemical, conservation, and literature data about protein binding pockets for drug-target triage. Useful as a reconnaissance step before computational binder design.

Enables managing PocketBase instances through intent-first tools for schema inspection, record CRUD, bulk operations, authentication, file handling, and server monitoring, with optional destructive operations gated behind explicit opt-in.

A local MCP server for interacting with a network lab, supporting read-only and configuration tools for devices like Arista EOS switches.