Model Context Protocol (MCP)
MCP is an open protocol introduced by Anthropic for connecting AI models to tools, data sources, and external systems in a standardized way. It enables safe, controlled access for agents and tools.
Definition
MCP provides a standard interface for connecting LLMs to external resources like databases, APIs, file systems, and web services. Rather than LLMs making arbitrary API calls, MCP defines how systems safely expose capabilities to models with appropriate permissions and resource limits. This enables secure integration of AI with enterprise systems.
MCP implementations expose resources as servers that models can query. An MCP server might expose a company's customer database, internal documentation, or APIs. The model can interact with these resources through the standardized MCP interface rather than learning unique API details for each integration.
Why it matters for AI visibility
MCP enables your data and APIs to be safely integrated into answer engines and agent workflows without exposing sensitive information. Brands can provide MCP servers that deliver real-time product information, current pricing, or documentation to AI systems, improving accuracy of citations and enabling dynamic answers.
Related terms
Function Calling (Tool Use)
Function Calling is the capability of LLMs to call external functions or APIs as part of generating responses. It enables agents to take actions, query databases, or access real-time information beyond the model's training.
AIAI Agents
AI Agents are autonomous systems that use LLMs to perceive their environment, make decisions, and take actions to accomplish goals. They can use tools, run code, and execute multi-step workflows without human intervention.
AIComputer Use
Computer Use is the capability of AI systems to see and interact with computers through screenshots and simulated input, enabling them to navigate websites and use software tools directly.
AIAgentic Workflows
Agentic Workflows are automated processes orchestrated by AI agents that execute multi-step tasks, make decisions between steps, and adapt to outcomes. They combine language understanding with action execution.