Model Context Protocol (MCP) is an open integration protocol that enables Framer Server API.AI agents to discover and use external tools, resources, and actions through MCP servers. If you want to learn more about how Framer integrates with MCP, check out the

An MCP Server is a service that implements the Model Context Protocol, making external capabilities available to compatible AI agents.

An MCP client is the part of an app or MCP server and requests tools, resources, or prompts using Model Context Protocol (MCP).agent that connects to an

A local MCP server is an MCP server that runs on the same machine as the MCP host, usually for low-latency access to local files, apps, or developer tools.

A hosted MCP server is a remote MCP server operated by a provider, letting an MCP client connect to tools or data without installing the server locally.

MCP authentication is the process of verifying identity when an MCP client connects to a remote MCP server, usually before permissions or tool access are granted.

MCP transport is the communication layer an MCP client uses to talk to an MCP server, such as local stdio or network-based HTTP transport.