Skip to content
#

MCP Server

MCP servers are lightweight programs that expose specific capabilities to AI applications through the Model Context Protocol (MCP). Each server acts as a bridge between AI models and external systems, providing tools (executable functions), resources (read-only data), and prompts (reusable templates) through a standardized interface.

MCP servers communicate with AI-powered clients over stdio for local processes or HTTP with Server-Sent Events for remote connections. They can integrate with databases, APIs, file systems, development tools, and cloud services. A single AI application can connect to multiple MCP servers simultaneously.

The MCP server ecosystem includes registries such as the official MCP Registry, Glama, and Smithery, where developers publish and discover servers for specific use cases.

Here are 28,488 public repositories matching this topic...

moodle-downloader

🎓 一键同步 UNSW Moodle 课件,然后让 AI 陪你复习 | Sync your Moodle course materials, then let AI revise them with you — built-in MCP server for Claude Code, Obsidian export, spaced-repetition planning

  • Updated Jul 28, 2026
  • Python