{"type":"mcp_server","name":"mcp-server-milvus","description":"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","category":"Database","language":"Python","stars":233,"forks":5,"owner":"zilliztech","github_url":"https://github.com/zilliztech/mcp-server-milvus","homepage":null,"setup":"## Setup\n\n1.  Ensure you have Python 3.10 or higher.\n2.  Ensure you have a running [Milvus](https://milvus.io/) instance (local or remote).\n3.  Ensure you have [uv](https://github.com/astral-sh/uv) installed (recommended for running the server).\n4.  Clone the repository: `git clone https://github.com/zilliztech/mcp-server-milvus.git` and `cd mcp-server-milvus`.\n5.  Run the server directly: `uv run src/mcp_server_milvus/server.py --milvus-uri http://localhost:19530`.\n6.  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`.\n7.  For Claude Desktop, install it and add the provided configuration to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS), then restart Claude Desktop.\n8.  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\n\n1.  `milvus_text_search`: Search for documents using full text search.\n2.  `milvus_vector_search`: Perform vector similarity search on a collection.\n3.  `milvus_query`: Query collection using filter expressions.\n4.  `milvus_list_collections`: List all collections in the database.\n5.  `milvus_create_collection`: Create a new collection with specified schema.\n6.  `milvus_load_collection`: Load a collection into memory for search and query.\n7.  `milvus_release_collection`: Release a collection from memory.\n8.  `milvus_insert_data`: Insert data into a collection.\n9.  `milvus_delete_entities`: Delete entities from a collection based on filter expression.","faq":null,"created_at":"2025-03-06T02:10:40+00:00","updated_at":"2025-03-28T10:15:33+00:00","source_url":"https://model-context-protocol.com/servers/mcp-server-milvus-llm-vector-database","related_articles":[]}