Last reviewed:
What is MCP (Model Context Protocol)? Definition and business implications
MCP (Model Context Protocol) is an open standard, introduced by Anthropic in November 2024, that lets an AI model connect to data sources and external tools in a uniform way. It avoids writing specific connectors for every model-application combination.
Before MCP, every company deploying an AI assistant had to code custom connectors: one for its CRM, one for its document base, one for its internal tools. Worse, these connectors had to be redone with each model change. MCP standardises this integration. It defines a client-server architecture: the LLM is the client, external tools (databases, business APIs, files) are exposed by MCP servers. An MCP server written once is usable by all compatible models. The protocol is open source, released under MIT licence by Anthropic, and was adopted in 2025 by OpenAI, Google, and most AI agent vendors. In 2026, several hundred MCP servers are publicly available, covering Slack, GitHub, Salesforce, Google Drive, and most standard enterprise SaaS tools.
Concrete example
A 40-employee accounting firm wants its AI assistant to query directly the accounting software (Sage, Cegid), the internal document management system, and the shared mailbox. Without MCP, that means three specific connectors to develop, that is, 6 to 8 weeks of development and about 25,000 euros, with ongoing maintenance. With MCP, three existing public MCP servers (one per tool) suffice, plugged in within a few days. Cost: less than 5,000 euros, maintenance handled by the server publishers. Better: if the firm decides to migrate from Claude to another model, no rewriting on the connector side, the standard protocol remains.
See also
Further reading
Sources
- Introducing the Model Context Protocol, Anthropic, November 2024. https://www.anthropic.com/news/model-context-protocol
- Model Context Protocol specification, version 2025. https://modelcontextprotocol.io/specification