Model Context Protocol (MCP)
Open protocol standardizing tool/data access for agents
Anthropic released the Model Context Protocol in late 2024 as an open standard for connecting models to tools and data sources, and by 2025 OpenAI, Google, and Microsoft had adopted it. MCP is becoming the 'USB-C of AI agents,' defining how the agent ecosystem interoperates. Whoever shapes the standard shapes the agent economy.
Origin
Anthropic (2024)
Adoption
OpenAI, Google, IDEs
Role
Agent-to-tool interoperability
How it fits the stack
Model Context Protocol (MCP) with what it depends on (above) and what it feeds (below). The figure renders as a crawlable diagram and upgrades to an interactive 3D graph as it scrolls into view.
Model Context Protocol (MCP) in the AI stack. Model Context Protocol (MCP) with its immediate upstream dependencies (top) and downstream dependents (bottom) in the AI value chain. Hover a node in 3D, or read the full relationships below.
Graph data (text) — 9 entities, 8 relationships
- Agent frameworks (LangChain, LlamaIndex, etc.) —uses→ Model Context Protocol (MCP)
- Agent Orchestration Frameworks —uses→ Model Context Protocol (MCP)
- Agentic AI / autonomous workflows —depends on→ Model Context Protocol (MCP)
- AI coding agents & IDEs —used by→ Model Context Protocol (MCP)
- Cursor (Anysphere) —uses→ Model Context Protocol (MCP)
- Google DeepMind —uses→ Model Context Protocol (MCP)
- LangChain / LangGraph —uses→ Model Context Protocol (MCP)
- Model Context Protocol (MCP) —designs→ Anthropic
Feeds ↓ · 9
Context — capital, rivals, policy · · 2