MCP (Model Context Protocol)
- Definition
- An open standard (created by Anthropic) that lets AI models connect to external tools, data sources, and services through a unified interface. MCP is becoming the USB-C of AI integrations.
- Why it matters
- MCP solves the N-times-M integration problem in AI. Without it, every AI application must build custom integrations for every data source and tool. With MCP, tool providers build one MCP server, and every AI application that supports MCP can use it. This is the same pattern that USB standardized for hardware peripherals. The strategic importance is in ecosystem effects: as more tools support MCP, the value of MCP-compatible AI applications increases, creating a network effect that benefits early adopters. Companies building AI products should support MCP consumption now and consider building MCP servers for their own products to become part of the emerging AI integration ecosystem.
- In practice
- Anthropic open-sourced MCP in November 2024, and adoption grew rapidly. By early 2026, MCP servers existed for GitHub, Slack, Google Drive, Notion, Postgres databases, file systems, and dozens of other services. OpenAI, Google, and Microsoft added MCP support to their platforms. The protocol defines three core primitives: tools (actions the model can take), resources (data the model can read), and prompts (templated instructions). In practice, an MCP-enabled AI assistant can search your codebase, query your database, send Slack messages, and create pull requests through a single protocol, without custom integration code for each service.
Seen in recent stories
Where MCP (Model Context Protocol) showed up in the last 90 days of KeyNews editions.
Quick answers
- What is MCP (Model Context Protocol)?
- An open standard (created by Anthropic) that lets AI models connect to external tools, data sources, and services through a unified interface. MCP is becoming the USB-C of AI integrations.
- Why does MCP (Model Context Protocol) matter?
- MCP solves the N-times-M integration problem in AI. Without it, every AI application must build custom integrations for every data source and tool. With MCP, tool providers build one MCP server, and every AI application that supports MCP can use it. This is the same pattern that USB standardized for hardware peripherals. The strategic importance is in ecosystem effects: as more tools support MCP, the value of MCP-compatible AI applications increases, creating a network effect that benefits early adopters. Companies building AI products should support MCP consumption now and consider building MCP servers for their own products to become part of the emerging AI integration ecosystem.
- How is MCP (Model Context Protocol) used in practice?
- Anthropic open-sourced MCP in November 2024, and adoption grew rapidly. By early 2026, MCP servers existed for GitHub, Slack, Google Drive, Notion, Postgres databases, file systems, and dozens of other services. OpenAI, Google, and Microsoft added MCP support to their platforms. The protocol defines three core primitives: tools (actions the model can take), resources (data the model can read), and prompts (templated instructions). In practice, an MCP-enabled AI assistant can search your codebase, query your database, send Slack messages, and create pull requests through a single protocol, without custom integration code for each service.
Related terms
Tool use
The ability of an AI model to invoke external tools, such as web search, code execution, or database queries, to augment its capabilities. Tool use transforms models from knowledge stores into action-taking agents.
Function calling
A model capability that lets the AI output structured tool invocations (API calls, database queries, etc.) rather than plain text. Function calling is what turns a chatbot into an agent that can take real-world actions.
Agent
An AI system that can autonomously plan, use tools, and execute multi-step tasks on behalf of a user. Agents are the next major product paradigm after chatbots, with every major lab shipping agent frameworks.
A2A (Agent-to-Agent)
A protocol that enables AI agents built by different vendors to discover, authenticate, and collaborate with each other. A2A standardizes how agents delegate sub-tasks, share context, and return results across organizational boundaries.
Tools that use this
Notion AI
AI agents and search inside your workspace
Cursor
AI-native code editor, now a SpaceX company
GitHub Copilot
Agentic AI coding platform across the dev lifecycle
Claude Code
Autonomous coding agent across terminal, IDE, and browser
v0
Prompt-to-app builder for Next.js and React
Devin Desktop
Cognition's agentic IDE, formerly Windsurf
Otter.ai
Meeting transcription and searchable conversation knowledge
Granola
Bot-free AI notepad that enhances your meeting notes
Zapier AI
Connect 9,000+ apps with AI-powered automation
Elicit
AI research assistant for systematic literature review
Hex
Agentic data notebooks for analytics teams
Microsoft Foundry
Microsoft's unified platform for enterprise AI agents
Know the terms. Know the moves.
ONE BRIEFING · EVERY FRIDAY · FREE
Free. Unsubscribe anytime.