1、前言

by AndyM129

1 stars
198 downloads
Not rated
GitHub

About

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…

Details

Author
AndyM129
GitHub stars
1
Downloads
198
Categories
Other

- 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].

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name 1、前言
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

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.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "1\u3001\u524d\u8a00": {
            "mcp_playground": {
                "command": "uv",
                "args": [
                    "version"
                ]
            }
        }
    }
}

McpServers

{
    "mcp_playground": {
        "command": "uv",
        "args": [
            "version"
        ]
    }
}

1、前言

大模型火了一阵子了,最近又火了一个技术 —— MCP

在看了一些介绍后,恰巧之前通过 Ollama 也部署了本地大模型,正好可以试试本地 MCP,兴许可以「以后 自己开发些 MCP,然后通过本地大模型调用」,这样就能摆脱 UI、Terminal 来执行特定的操作了~~

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.