Anthropic, a developer of AI models and related tools, launched Model Context Protocol (MCP), an open-source standard that connects AI assistants to data systems. The protocol is available to all developers, while Claude Enterprise plan subscribers can connect Claude chatbot to their internal systems via MCP servers.

MCP enables two-way connections between data sources and AI applications through MCP servers and clients. The protocol includes three main components: specification and SDKs, local MCP server support in Claude Desktop apps, and an open-source repository of MCP servers. Anthropic has also provided pre-built MCP servers for enterprise systems like Google Drive, Slack, GitHub, Git, Postgres, and Puppeteer.

Analyst QuickTake: MCP eliminates the need for maintaining separate connectors for each data source, allowing AI systems to maintain context while moving between different tools and datasets. The need for such a protocol has become increasingly apparent as businesses and organizations face the challenge of integrating AI chatbots and assistants into their existing technology stacks. Traditionally, these AI-powered tools have often operated in isolation, unable to fully leverage the data and information available within an organization. Anthropic's MCP aims to address this issue by providing a standardized framework for data connectivity and accessibility.