Milvus
Model Context Protocol Servers for Milvus
What is Milvus?
Milvus is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol servers for milvus
Model Context Protocol Servers for Milvus
This server falls under the Databases category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Model Context Protocol Servers for Milvus
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx milvusConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Milvus
The Milvus MCP Server connects AI assistants directly to Milvus — the open-source vector database — exposing tools for text search, vector similarity search, hybrid search, collection management, and data insertion through a natural language interface. It supports multiple search metric types (COSINE, L2, IP) and works with both local Milvus instances and the managed Zilliz Cloud service. AI engineers and data scientists use it to let LLMs query and manage their vector stores for RAG pipelines, semantic search applications, and embedding management without writing Python code.
Prerequisites
- A running Milvus instance (local via Docker or a Zilliz Cloud account)
- Python 3.10+ and the uv package manager installed
- The mcp-server-milvus repository cloned locally
- An MCP-compatible AI client such as Claude Desktop or Cursor
- Optional: MILVUS_TOKEN if your Milvus instance requires authentication (e.g., Zilliz Cloud)
Start a Milvus instance
If you do not have Milvus running, start a local instance with Docker. For production, consider Zilliz Cloud.
# Quickstart with Docker:
docker run -d --name milvus-standalone \
-p 19530:19530 \
milvusdb/milvus:latest standaloneClone the mcp-server-milvus repository
Clone the official repository from Zilliz to get the server source and configuration files.
git clone https://github.com/zilliztech/mcp-server-milvus.git
cd mcp-server-milvusTest the server locally
Run the server directly with uv to confirm it connects to your Milvus instance before configuring an MCP client.
uv run src/mcp_server_milvus/server.py --milvus-uri http://localhost:19530Configure the server in your MCP client
Add the Milvus MCP server to your client configuration. Set MILVUS_URI and optionally MILVUS_TOKEN and MILVUS_DB.
Restart your MCP client and verify
Restart Claude Desktop or your MCP client to load the Milvus server. Ask it to list collections to confirm the connection is working.
Milvus Examples
Client configuration
Add the Milvus MCP server to Claude Desktop, connecting to a local Milvus instance.
{
"mcpServers": {
"milvus": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-server-milvus",
"run",
"src/mcp_server_milvus/server.py",
"--milvus-uri",
"http://localhost:19530"
],
"env": {
"MILVUS_TOKEN": "",
"MILVUS_DB": "default"
}
}
}
}Client configuration for Zilliz Cloud
Connect to a managed Zilliz Cloud cluster using the public endpoint and API key as the token.
{
"mcpServers": {
"milvus": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-server-milvus",
"run",
"src/mcp_server_milvus/server.py",
"--milvus-uri",
"https://your-cluster.zillizcloud.com"
],
"env": {
"MILVUS_TOKEN": "your-zilliz-api-key",
"MILVUS_DB": "default"
}
}
}
}Prompts to try
Use these prompts with your AI assistant once Milvus is connected.
- "List all collections in my Milvus database."
- "Create a new collection called 'articles' with fields for title (VARCHAR), content (VARCHAR), and embedding (FLOAT_VECTOR, 128 dimensions)."
- "Find documents in the text_collection that are semantically similar to 'machine learning for healthcare'."
- "Insert this record into the articles collection: title='Intro to RAG', content='RAG combines retrieval with generation'."
- "Search the embeddings collection for the 5 nearest neighbors to this vector using cosine similarity."Troubleshooting Milvus
Connection refused when trying to reach http://localhost:19530
Make sure your Milvus Docker container is running: 'docker ps | grep milvus'. If the container is not listed, start it again. Port 19530 must be exposed and not blocked by a local firewall.
Authentication error when connecting to Zilliz Cloud
Set MILVUS_TOKEN to your Zilliz Cloud API key (found in the Cloud Console under API Keys). The MILVUS_URI must be the public endpoint URL of your specific cluster, not a generic URL.
.env file values are ignored
The server documentation notes that .env file values take higher priority than command-line arguments. If you have a .env file in the mcp-server-milvus directory with MILVUS_URI set, it will override the --milvus-uri flag. Remove conflicting entries from .env or update them to match your target instance.
Frequently Asked Questions about Milvus
What is Milvus?
Milvus is a Model Context Protocol (MCP) server that model context protocol servers for milvus It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Milvus?
Follow the installation instructions on the Milvus GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Milvus?
Milvus works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Milvus free to use?
Yes, Milvus is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Milvus Alternatives — Similar Databases Servers
Looking for alternatives to Milvus? Here are other popular databases servers you can use with Claude, Cursor, and VS Code.
Excelize
★ 20.6kGo language library for reading and writing Microsoft Excel™ (XLAM / XLSM / XLSX / XLTM / XLTX) spreadsheets
MCP Toolbox for Databases
★ 15.3kOpen source MCP server specializing in easy, fast, and secure tools for Databases.
DBHub
★ 2.8kA universal database gateway MCP server that enables AI assistants to connect to and query multiple databases (PostgreSQL, MySQL, MariaDB, SQL Server, SQLite) with support for schema exploration, SQL execution, and secure connections via SSH tunnels.
Tabularis
★ 2.1kA lightweight, cross-platform database client for developers. Supports MySQL, PostgreSQL and SQLite. Hackable with plugins. Built for speed, security, and aesthetics.
Postgres AI Guide
★ 1.7kMCP server and Claude plugin for Postgres skills and documentation. Helps AI coding tools generate better PostgreSQL code.
Anyquery
★ 1.7k🏎️ 🏠 ☁️ - Query more than 40 apps with one binary using SQL. It can also connect to your PostgreSQL, MySQL, or SQLite compatible database. Local-first and private by design.
Browse More Databases MCP Servers
Explore all databases servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Milvus in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Milvus?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.