MCP Servers
63,654 MCP servers for AI apps. Filter by category, badge and popularity.
Developer Tools
One persistent tmux-backed terminal for AI agents. ssh, docker exec, and REPLs nest inside a single authenticated session (no re-auth per command). Token-reduced reads, 4-layer completion detection, and a human can co-drive via the shared tmux socket. Install: npx -y aiterm-mcp
Use build-my-own to replicate any GitHub project. It sets up the directory structure, prompts, and rules for AI, enabling it to assist you—more like guiding you—to recreate your desired project from scratch. Throughout the process, you'll collaborate with AI to think through the
API intelligence for AI coding agents. CLIRank scores 387 APIs on agent-friendliness: auth method, CLI tools, headless operation, pricing transparency. Six MCP tools for API discovery, comparison, scoring, and docs retrieval. Built for Claude Code, Cursor, Copilot, Codex, and Win
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
