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.
Explanation
Tools are the most commonly used MCP primitive and typically the best starting point when building an MCP server. Each tool has a name, a description (which AI uses to decide when to call it), and a typed input schema (which tells AI what parameters are needed). When an AI assistant determines that a tool is relevant to the user's request, it calls the tool with the required parameters. The MCP server executes the operation and returns the result. Good tool design is critical — the name should describe what the tool does (not how it's implemented), the description should explain when to use it, and the input schema should request complete task information rather than implementation details. Tools that represent complete user tasks (like 'create-issue' rather than 'POST-to-endpoint') are easier for AI to use effectively.
Related Terms
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.
MCP Resources
MCP Resources expose read-only data to AI assistants. They let AI models query databases, read files, fetch configurations, or access any data from your system — without performing mutations or side effects.
MCP Prompts
MCP Prompts are guided workflows that an MCP server exposes to AI assistants. They define multi-step processes — like onboarding a new user, debugging an issue, or generating a report — that combine your tool's capabilities with structured AI guidance.
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.
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.