Tutorials
Step-by-step guides to get you started with gomcptest
gomcptest is a proof of concept (POC) demonstrating how to implement a Model Context Protocol (MCP) with a custom-built host to play with agentic systems.
Welcome to the gomcptest documentation. This project is a proof of concept (POC) demonstrating how to implement a Model Context Protocol (MCP) with a custom-built host to play with agentic systems.
Our documentation follows the Divio Documentation Framework, which organizes content into four distinct types: tutorials, how-to guides, reference, and explanation. This approach ensures that different learning needs are addressed with the appropriate content format.
Tutorials are lessons that take you by the hand through a series of steps to complete a project. They focus on learning by doing, and help beginners get started with the system.
Tutorial | Description |
---|---|
Getting Started with gomcptest | A complete beginner’s guide to setting up the environment, building tools, and running your first agent. Perfect for first-time users. |
Building Your First OpenAI-Compatible Server | Step-by-step instructions for running and configuring the OpenAI-compatible server that communicates with LLM models and executes MCP tools. |
Using the cliGCP Command Line Interface | Hands-on guide to setting up and using the cliGCP tool to interact with LLMs and perform tasks using MCP tools. |
How-to guides are recipes that guide you through the steps involved in addressing key problems and use cases. They are practical and goal-oriented.
How-to Guide | Description |
---|---|
How to Create a Custom MCP Tool | Practical steps to create a new custom tool compatible with the Model Context Protocol, including code templates and examples. |
How to Configure the OpenAI-Compatible Server | Solutions for configuring and customizing the OpenAI server for different use cases, including environment variables, tool configuration, and production setup. |
How to Configure the cliGCP Command Line Interface | Guides for customizing the cliGCP tool with environment variables, command-line arguments, and specialized configurations for different tasks. |
Reference guides are technical descriptions of the machinery and how to operate it. They describe how things work in detail and are accurate and complete.
Reference | Description |
---|---|
Tools Reference | Comprehensive reference of all available MCP-compatible tools, their parameters, response formats, and error handling. |
OpenAI-Compatible Server Reference | Technical documentation of the server’s architecture, API endpoints, configuration options, and integration details with Vertex AI. |
cliGCP Reference | Detailed reference of the cliGCP command structure, components, parameters, interaction patterns, and internal states. |
Explanation documents discuss and clarify concepts to broaden the reader’s understanding of topics. They provide context and illuminate ideas.
Explanation | Description |
---|---|
gomcptest Architecture | Deep dive into the system architecture, design decisions, and how the various components interact to create a custom MCP host. |
Understanding the Model Context Protocol (MCP) | Exploration of what MCP is, how it works, design decisions behind it, and how it compares to alternative approaches for LLM tool integration. |
gomcptest consists of several key components that work together:
host/openaiserver
): A server that implements the OpenAI API interface and connects to Google’s Vertex AI for model inference.host/cliGCP
): A command-line interface similar to Claude Code or ChatGPT that interacts with Gemini models and MCP tools.The tools
directory contains various MCP-compatible tools:
Step-by-step guides to get you started with gomcptest
Practical guides for solving specific problems with gomcptest
Technical reference documentation for gomcptest components and tools
Understanding-oriented content for gomcptest architecture and concepts
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.