Tool Calling
Tool calling (also called function calling) is the mechanism by which AI models invoke external functions or APIs. MCP standardizes tool calling across AI providers, making it consistent, discoverable, and secure rather than provider-specific.
Explanation
Tool calling is the bridge between AI reasoning and real-world actions. When an AI model determines that it needs to perform an operation — like searching a database, creating an issue, or deploying code — it generates a structured tool call with the function name and parameters. The host application executes the call and returns the result. Without MCP, tool calling is implemented differently by each AI provider (OpenAI, Anthropic, Google all have their own function calling APIs), and each tool integration is a custom implementation. MCP standardizes this: you define your tools once in an MCP server, and any MCP-compatible AI client can discover and use them. This eliminates the need to build separate integrations for each AI provider.
Related Terms
MCP Tools
MCP Tools are the action primitive in the Model Context Protocol. They let AI assistants perform operations — creating records, triggering deployments, sending messages, or any other action your service supports — by calling structured functions on your MCP server.
Model Context Protocol (MCP)
Model Context Protocol (MCP) is an open standard that defines how AI assistants connect to external tools, data sources, and services. It provides a structured way for AI models to discover, understand, and use capabilities from any MCP-compatible server.
Ready to build your own MCP server?
Take the 2-minute quiz to find out if MCP is the right fit for your project, then get a step-by-step plan to ship it.