MCP guides

What is MCP (Model Context Protocol)? A plain-English guide

What the Model Context Protocol is, how MCP clients and servers work, and why it matters for AI agents.

Add any MCP server to Claude Desktop: where claude_desktop_config.json lives on macOS and Windows, an example config, and troubleshooting.

Add local and remote MCP servers to Cursor with ~/.cursor/mcp.json or a project .cursor/mcp.json, with examples.

Set up MCP servers in VS Code with .vscode/mcp.json, the MCP: Add Server command and Copilot agent mode.

A practical security checklist for MCP servers: trust, version pinning, least privilege, secrets, prompt injection and tool poisoning.

Build, test and connect a minimal MCP server with the official Python SDK and MCPServer, plus design tips.

Add local and remote MCP servers to Claude Code with claude mcp add, choose a scope, and check them with /mcp.

Configure MCP servers for the Codex CLI, IDE extension and app with codex mcp add or ~/.codex/config.toml.

LM Studio 0.3.17+ supports local and remote MCP servers via mcp.json, using the same format as Cursor.

Configure local and remote MCP servers in OpenCode with the mcp object in opencode.json.

Function calling is how a model asks to use a tool; MCP is a standard way to package and share those tools across apps.

RAG retrieves text to put in the prompt; MCP connects a model to live tools and data. They solve different problems and work well together.

MCP connects an agent to tools and data; A2A (Agent2Agent) lets independent agents discover each other and delegate tasks.

An API is built for programmers; an MCP server describes tools so that AI models can find and call them safely.