What is Model Context Protocol (MCP)?

Model Context Protocol (MCP)

Model Context Protocol (MCP) is an open standard from Anthropic for connecting AI assistants to external data, content, and tools in a uniform way​. The idea behind MCP is to give a language model access to a wide range of context -- think documents, databases, APIs, etc. -- through a single protocol instead of bespoke integrations for each source. Under MCP, developers run MCP servers that expose data or services, and AI applications (MCP clients) query those servers for relevant information​.

Example

Example: An AI assistant (MCP client) connects to various data source servers via the Model Context Protocol (MCP). The assistant on the left issues MCP requests (arrows) to servers exposing a database, a code repository, and a chat platform, retrieving relevant context from each. MCP standardizes these tool/API interactions (like a “USB-C” for AI data access​). In the diagram, arrows labeled “MCP” indicate secure, two-way data exchange. This allows the LLM assistant to augment its responses with fresh data (files, knowledge bases) -- bridging isolated data silos by using a single open protocol for tool-use and context injection.