MCP
Model Context Protocol — an open protocol introduced by Anthropic in November 2024 that lets LLM clients (editors, agents, assistants) connect to external tools and data sources through a standard JSON-RPC interface.
Background
MCP standardises how AI applications expose tools, resources, and prompts to LLM clients. A client (Claude Desktop, Cursor, Claude Code) launches one or more MCP servers, each providing a typed set of capabilities (e.g. file search, database query, GitHub API). The protocol is JSON-RPC 2.0 over stdio or HTTP, language-agnostic, and supports streaming. MCP has been adopted by Anthropic, OpenAI, Google, and most major coding agents, making it the de-facto interoperability standard for LLM tool use as of 2026.
Tools that use it
- 01→Cursor
VS Code-based, agent-first coding environment — since Cursor 3.0 the default surface is an Agents Window, not an editor.
- 02→Continue
Open-source AI code assistant for VS Code and JetBrains, with full BYOK and local-model support.
- 03→Cline
Open-source autonomous coding agent for VS Code, formerly known as Claude Dev.
- 04→Claude Code
Anthropic's official CLI agent for Claude — runs in the terminal, edits files, executes commands, and ships PRs.