Cover image
MCP-Pymilvus-code-Generate-Helper
Public

MCP-Pymilvus-code-Generate-Helper

Try Now
2025-04-08

具有基于SSE的MCP支持的Pimilvus代码生成助手

3 years

Works with Finder

2

Github Watches

2

Github Forks

0

Github Stars

mcp-pymilvus-code-generate-helper

A Model Context Protocol server that retrieves relevant code snippets or documents to help generating pymilvus code.

Architecture

Example

Prerequisites

Before using this MCP server, ensure you have:

  • Python 3.10 or higher
  • A running Milvus instance (local or remote)
  • uv installed (recommended for running the server)

Usage

The recommended way to use this MCP server is to run it directly with uv without installation. This is how both Claude Desktop and Cursor are configured to use it in the examples below. The server now support both sse and stdio:

SSE

Running the Server

uv run src/mcp_pymilvus_code_generate_helper/sse_server.py
# mcp server will connect to local milvus server(http://localhost:19530) by default if no milvus_uri is provided
# to connect to a remote milvus server, you can specify the milvus_uri like this:
# uv run src/mcp_pymilvus_code_generate_helper/sse_server.py --milvus_uri http://<your-server-ip>:<your-server-port>

Usage with Cursor

  1. Go to Cursor > Preferences > Cursor Settings > MCP
  2. Click on the + Add New MCP Server button
  3. Fill out the form:
    • Name: pymilvus-code-generate-helper (or any name you prefer)
    • Type: Select sse
    • Server URL: http://localhost:23333/sse (replace with your server's IP address)
  4. Click Save

You can also directly edit mcp.json as below:

{
  "mcpServers": {
    "pymilvus-code-generate-helper": {
      "url": "http://localhost:23333/sse"
    }
  }
}

Usage with Claude Desktop

⚠️ Claude desktop is currently limited in its ability to connect to remote MCP servers

STDIO

Running the Server

uv run src/mcp_pymilvus_code_generate_helper/stdio_server.py
# mcp server will connect to local milvus server(http://localhost:19530) by default if no milvus_uri is provided
# to connect to a remote milvus server, you can specify the milvus_uri like this:
# uv run src/mcp_pymilvus_code_generate_helper/stdio_server.py --milvus_uri http://<your-server-ip>:<your-server-port>

Usage with Cursor

  1. Go to Cursor > Preferences > Cursor Settings > MCP
  2. Click on the + Add New MCP Server button
  3. Fill out the form:
    • Name: pymilvus-code-generate-helper (or any name you prefer)
    • Type: Select stdio
    • Command: /PATH/TO/uv --directory /path/to/mcp-pymilvus-code-generator run src/mcp_pymilvus_code_generate_helper/stdio_server.py
  4. Click Save

You can also directly edit mcp.json as below:

{
  "mcpServers": {
    "pymilvus-code-generate-helper": {
      "command": "/PATH/TO/uv",
      "args": [
        "--directory",
        "/path/to/mcp-pymilvus-code-generator",
        "run",
        "src/mcp_pymilvus_code_generate_helper/stdio_server.py",
        "--milvus_uri",
        "http://localhost:19530"
      ],
      "env": {
        "OPENAI_API_KEY": "YOUR OPENAI API KEY HERE"
      }
    }
  }
}

Usage with Claude Desktop

  1. Install Claude Desktop from https://claude.ai/download
  2. Open your Claude Desktop configuration:
    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  3. Add the following configuration:
{
  "mcpServers": {
    "pymilvus-code-generate-helper": {
      "command": "/PATH/TO/uv",
      "args": [
        "--directory",
        "/path/to/mcp-server-milvus/src/mcp_server_milvus",
        "run",
        "src/mcp_pymilvus_code_generate_helper/stdio_server.py",
        "--milvus_uri",
        "http://localhost:19530"
      ], 
      "env": {
        "OPENAI_API_KEY": "YOUR OPENAI API KEY HERE"
      }
    }
  }
}
  1. Restart Claude Desktop

⚠️ Note: Remember to set the OPENAI_API_KEY environment variable

Available Tools

The server provides the following tools:

  • milvus-pypmilvus-code-generate-helper: Find related pymilvus code/documents to help generating code from user input in natural language

    • Parameters:
      • query: User query for generating code
  • milvus-translate-orm-to-milvus-client-code-helper: Find related orm and pymilvus client code/documents to help translating orm code to milvus client from user input in natural language

    • Parameters:
      • query: User query for translating orm code to milvus client code

Contribution

Contributions are welcome! If you have ideas for improving the retrieve result, please submit a pull request or open an issue.

License

This project is licensed under the MIT License.

相关推荐

  • NiKole Maxwell
  • I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

  • Bora Yalcin
  • Evaluator for marketplace product descriptions, checks for relevancy and keyword stuffing.

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Callycode Limited
  • A geek-themed horoscope generator blending Bitcoin prices, tech jargon, and astrological whimsy.

  • Alexandru Strujac
  • Efficient thumbnail creator for YouTube videos

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • Khalid kalib
  • Write professional emails

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Lists Tailwind CSS classes in monospaced font

  • apappascs
  • 发现市场上最全面,最新的MCP服务器集合。该存储库充当集中式枢纽,提供了广泛的开源和专有MCP服务器目录,并提供功能,文档链接和贡献者。

  • ShrimpingIt
  • MCP系列GPIO Expander的基于Micropython I2C的操作,源自ADAFRUIT_MCP230XX

  • OffchainLabs
  • 进行以太坊的实施

  • huahuayu
  • 统一的API网关,用于将多个Etherscan样区块链Explorer API与对AI助手的模型上下文协议(MCP)支持。

  • deemkeen
  • 用电源组合控制您的MBOT2:MQTT+MCP+LLM

    Reviews

    5 (1)
    Avatar
    user_rlJbueiq
    2025-04-15

    I have been using the CODING DevOps MCP Server for a while now, and it has significantly streamlined my development and deployment processes. The server is robust, efficient, and incredibly user-friendly. Kudos to yupengfei1209 for creating such a fantastic tool that integrates seamlessly into my workflow. Highly recommend checking it out: https://mcp.so/server/coding_devops_mcp_server/yupengfei1209