What are the prerequisites?
Python 3.10 or higher, a running Milvus instance (local or remote), and `uv` installed.
@brcarry
A pimilvus code generating helper with SSE-based MCP support
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-pymilvus-code-generator": {
"command": "uv",
"args": [
"run",
"src/mcp_pymilvus_code_generate_helper/sse_server.py"
]
}
}
}Find related pymilvus code/documents to help generating code from user input in natural language
Find related orm and pymilvus client code/documents to help converting orm code to pymilvus client (or vice versa)
Find related documents and code snippets in different programming languages for milvus code translation
`query`: A string of Milvus API names in list format to translate from one programming language to another (e.g., ['create_collection', 'insert', 'search'])
An MCP server that retrieves relevant code snippets or documents to help generate pymilvus code. It integrates with a running Milvus instance and is intended for developers using AI coding assistants like Cursor or Claude Desktop.
Run the server with uv run src/mcp_pymilvus_code_generate_helper/sse_server.py (for SSE) or uv run src/mcp_pymilvus_code_generate_helper/stdio_server.py (for STDIO). Configure it in Cursor or Claude Desktop by adding an MCP server entry. The server connects to a local Milvus instance by default; use --milvus_uri to specify a remote one.
Python 3.10 or higher, a running Milvus instance (local or remote), and `uv` installed.
Yes, the `OPENAI_API_KEY` environment variable must be set when using the STDIO configuration (e.g., in Claude Desktop or Cursor).
It supports both SSE (Server-Sent Events) and STDIO (standard input/output).
Yes, a Dockerfile is provided. Build the image with `docker build -t milvus-code-helper .` and run with environment variables for `OPENAI_API_KEY`, `MILVUS_URI`, and `MILVUS_TOKEN`.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Launch your product from your AI agent. Connect Claude Code, Codex, Cursor or ChatGPT to Launchdog over MCP and your agent drafts the listing, picks a launch week and books it. 50 launches a week, ranked only by human vo
Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up

Pugi is an AI product team in your chat. Describe a business in a few sentences and Pugi plans, designs, builds and checks a real website, shows a live preview, and puts it live on its own address. Ask for changes in pla
评论