1、前言

What is 1、前言?

1、前言 is a tutorial-style guide for setting up a local MCP (Model Context Protocol) server using Ollama and CherryStudio, aimed at developers who want to experiment with local large language models and MCP tools. It walks through installing dependencies, creating a simple Python MCP server named "hello-mcp-server", integrating it with CherryStudio, and testing the connection.

How to use 1、前言?

Follow the steps in the guide: install Ollama and a model (e.g., phi4), install CherryStudio, install uv, initialize a Python project with mcp[cli], write a tool using FastMCP, run mcp dev hello_mcp_server.py, then add the MCP server in CherryStudio and enable it in a conversation.

Key features of 1、前言

• Provides a step-by-step MCP setup tutorial for local LLMs.
• Uses Ollama as the local model backend.
• Integrates with CherryStudio as the client.
• Demonstrates creating a custom MCP tool with Python.
• Includes debugging via MCP Inspector.
• Covers installation of uv and mcp[cli].

Use cases of 1、前言

• Developers learning to build and test custom MCP servers locally.
• Experimenting with local LLMs (e.g., Llama, DeepSeek) via MCP tools.
• Creating simple automation tools that can be called from a chat interface.
• Testing MCP server integration with CherryStudio before deploying to production.

FAQ from 1、前言

What is the purpose of this guide?

It helps users set up a local MCP server using Ollama and CherryStudio, and provides a minimal Python example (hello-mcp-server) to get started.

What tools and dependencies are required?

You need Ollama, a local model, CherryStudio, Python, uv (package manager), and the mcp[cli] package. The guide installs all dependencies step by step.

How do I debug the MCP server?

Run mcp dev hello_mcp_server.py to start the MCP Inspector, then access http://127.0.0.1:6274 in a browser to connect and test tools.

How do I integrate the MCP server with CherryStudio?

In CherryStudio, add a new MCP server with the command uv run hello_mcp_server.py (or similar), then set a large model (e.g., Ollama's phi4), and enable the MCP server in a conversation.

Is this guide for a production-ready MCP server?

No, it is a basic tutorial for local testing and development. The example server only responds to a simple greeting tool.