Model Context Protocol (MCP)
MCP is an open standard that lets AI models connect to external tools and data sources through a unified interface - the USB-C of AI integrations.
Model Context Protocol (MCP) is an open standard that enables AI models to connect with external data sources and tools through a unified interface, providing context and capabilities beyond their training data.
Standardized Connectivity
MCP provides a single protocol for connecting AI models to any external tool - replacing custom integrations with a universal standard.
Tool Discovery
AI agents discover available tools and their capabilities dynamically, adapting to new integrations without reconfiguration.
Context Injection
External data sources feed relevant context to the AI model at query time - documents, database records, API responses.
Security Controls
MCP includes authentication and authorization at the protocol level. Each tool connection has defined permissions.
Bidirectional Communication
Not just read access - MCP supports both reading from and writing to external systems through the same protocol.
Composable Architecture
Mix and match MCP servers for different tools. Add new capabilities by adding servers, not rewriting integrations.
FAQ
Who created MCP?
Anthropic introduced MCP as an open standard. It is designed to be model-agnostic - any AI system can implement MCP clients to connect with MCP servers.
Is MCP required for AI agents?
No. AI agents can use custom API integrations. MCP provides a standardized approach that reduces integration complexity, especially when connecting to many tools.
Does OpenClaw use MCP?
OpenClaw supports MCP as one of several integration methods. For tools with MCP servers, setup is faster and more standardized.
Connect your tools via MCP
Learn how MCP powers AI agent integrations.