MCP Basics
What is the Model Context Protocol and how does it work?
What is MCP?
MCP (Model Context Protocol) is an open standard that lets AI models interact with external tools and data sources through a unified interface. It uses JSON-RPC 2.0 over HTTP, providing a structured request/response pattern that any language or platform can implement. Think of it as a universal plugin system — any MCP-compliant client can connect to any MCP-compliant server, regardless of who built either side.
How It Works
The MCP protocol defines three core concepts:
- TTools — Functions the server exposes that clients can call. SkillzDrive provides 11 tools for skill discovery, documentation, script execution, and session management. This is the primary capability used by the SkillzDrive server.
- RResources — Data the server provides that clients can read. Some MCP servers use this for static content.
- PPrompts — Pre-built templates for common tasks. Some MCP servers use these to guide AI through workflows.
What You Need
An MCP client
A library or built-in support in your platform. Claude.ai, Claude Code, Claude Desktop, Cursor, and ChatGPT all have MCP support built in. For custom agents, use an official SDK.
A transport
Streamable HTTP is recommended for remote servers like SkillzDrive. It's the modern MCP transport and what most clients use by default.
Authentication
A SkillzDrive API key, passed as a Bearer token in the Authorization header. Get one from your Account dashboard.
MCP Client Libraries
| Language | Package | Links |
|---|---|---|
| TypeScript | @modelcontextprotocol/sdk | GitHub |
| Python | mcp | GitHub |
| Kotlin | io.modelcontextprotocol:kotlin-sdk | GitHub |
| C# | ModelContextProtocol | GitHub |
Official Resources
MCP Documentation
- MCP Specification — The full protocol reference
- Build an MCP Client — Official tutorial for building your own client
- MCP GitHub — SDKs, examples, and the spec itself
You don't need to be an MCP expert