# mcp-server-milvus

> MCP Server

This repository provides an MCP server for Milvus, enabling seamless integration between LLM applications like Claude and Cursor, and the Milvus vector database. It allows LLMs to access external data

## Overview

- **Category:** Database
- **Language:** Python
- **Stars:** 240
- **Forks:** 5
- **Owner:** zilliztech
- **GitHub:** https://github.com/zilliztech/mcp-server-milvus
- **Created:** 2025-03-06T02:10:40+00:00
- **Updated:** 2025-03-28T10:15:33+00:00
- **Source:** https://model-context-protocol.com/servers/mcp-server-milvus-llm-vector-database

## Setup

## Setup

1.  Ensure you have Python 3.10 or higher.
2.  Ensure you have a running [Milvus](https://milvus.io/) instance (local or remote).
3.  Ensure you have [uv](https://github.com/astral-sh/uv) installed (recommended for running the server).
4.  Clone the repository: `git clone https://github.com/zilliztech/mcp-server-milvus.git` and `cd mcp-server-milvus`.
5.  Run the server directly: `uv run src/mcp_server_milvus/server.py --milvus-uri http://localhost:19530`.
6.  Alternatively, change the .env file in the `src/mcp_server_milvus/` directory to set the environment variables and run the server with `uv run src/mcp_server_milvus/server.py`.
7.  For Claude Desktop, install it and add the provided configuration to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS), then restart Claude Desktop.
8.  For Cursor, add the Milvus MCP server either through the Cursor Settings UI or by creating a `.cursor/mcp.json` file in your project root with the provided content, then restart Cursor or reload the window.

## Tools

## Available Tools

1.  `milvus_text_search`: Search for documents using full text search.
2.  `milvus_vector_search`: Perform vector similarity search on a collection.
3.  `milvus_query`: Query collection using filter expressions.
4.  `milvus_list_collections`: List all collections in the database.
5.  `milvus_create_collection`: Create a new collection with specified schema.
6.  `milvus_load_collection`: Load a collection into memory for search and query.
7.  `milvus_release_collection`: Release a collection from memory.
8.  `milvus_insert_data`: Insert data into a collection.
9.  `milvus_delete_entities`: Delete entities from a collection based on filter expression.