MCP and Protocols

The Model Context Protocol (MCP) is an open standard that gives AI models a universal interface for connecting to external tools, data sources, and services, analogous to how USB-C gives hardware a universal connector. Instead of building custom integrations for every tool-and-model combination, developers write one MCP server that any conforming client, including Cursor, Claude Desktop, and future agents, can discover and use without modification.

Tools are one of the Model Context Protocol's (MCP) three server primitives, representing executable actions that an agent can discover and invoke through the protocol, such as querying a database, creating a file, sending a message, or triggering a deployment. Each tool carries a name, description, and JSON Schema for its input parameters, following the same patterns as native function calling but standardized across MCP so any conforming client can use any conforming server's tools.

Resources are one of the Model Context Protocol's (MCP) three server primitives, representing data that a server exposes for an agent to read, such as files, database records, API responses, or live system state, identified by URIs that the agent or client retrieves on demand. Unlike tools, which perform actions, resources are passive data sources that let agents dynamically discover and pull in relevant information rather than requiring everything pre-loaded into the initial context.