Zilliz Cloud MCP
A Model Context Protocol (MCP) server seamlessly connecting AI Agents and AI coding tools with Zilliz Cloud https://zilliz.com/
What is Zilliz Cloud MCP?
Zilliz Cloud MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server seamlessly connecting ai agents and ai coding tools with zilliz cloud https://zilliz.com/
A Model Context Protocol (MCP) server seamlessly connecting AI Agents and AI coding tools with Zilliz Cloud https://zilliz.com/
This server falls under the Databases and Data Science & ML categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Model Context Protocol (MCP) server seamlessly connecting
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx zillizConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Zilliz Cloud MCP
Zilliz MCP Server is a Python MCP server that connects AI agents to Zilliz Cloud and self-hosted Milvus vector database instances, providing tools to manage clusters, databases, and collections, and to insert data and run vector similarity searches through natural language. It supports both stdio and streamable HTTP transport modes and uses a Zilliz Cloud API token for authentication. Data engineers and developers use it to build and test vector search pipelines, provision new clusters, and query existing collections without writing SDK code directly.
Prerequisites
- Python 3.10 or higher
- uv package manager (`curl -LsSf https://astral.sh/uv/install.sh | sh`)
- A Zilliz Cloud account with an API key (cloud.zilliz.com > Settings > API Keys)
- An MCP-compatible client such as Claude Desktop, Cursor, or Windsurf
Sign up for Zilliz Cloud and obtain an API key
Create a free account at cloud.zilliz.com, then go to Settings > API Keys to generate a token.
Configure stdio mode (recommended for local use)
Add the Zilliz MCP server to your MCP client config using uvx in stdio mode. This is the simplest setup — no manual clone required.
Alternative: clone and run in HTTP mode
Clone the repository and start the server as a standalone HTTP service on port 8000.
git clone https://github.com/zilliztech/zilliz-mcp-server.git
cd zilliz-mcp-server
cp example.env .env
# Edit .env: ZILLIZ_API_KEY="your_api_key_here"
uv run src/zilliz_mcp_server/server.py --transport streamable-httpVerify available tools
Ask your AI agent to list the available Zilliz tools to confirm the server is connected. You should see control plane tools (list_clusters, create_free_cluster) and data plane tools (search, insert_entities).
Create your first cluster
Use natural language to provision a free-tier Milvus cluster on Zilliz Cloud directly from your AI client.
Zilliz Cloud MCP Examples
Client configuration
Claude Desktop or Cursor configuration for the Zilliz MCP server in stdio mode using uvx.
{
"mcpServers": {
"zilliz-mcp-server": {
"command": "uvx",
"args": ["zilliz-mcp-server"],
"env": {
"ZILLIZ_CLOUD_TOKEN": "your-zilliz-cloud-api-token"
}
}
}
}Prompts to try
Example prompts that exercise Zilliz Cloud cluster management and vector search.
- "Create a free Milvus cluster on Zilliz Cloud called 'dev-cluster'."
- "List all my Zilliz Cloud clusters and show their status."
- "Create a collection called 'product_embeddings' with a 1536-dimensional float vector field."
- "Insert these 10 product embeddings into the product_embeddings collection."
- "Search the product_embeddings collection for items semantically similar to 'wireless noise-cancelling headphones'."Troubleshooting Zilliz Cloud MCP
Server fails with 'Authentication failed' when calling Zilliz APIs
Verify ZILLIZ_CLOUD_TOKEN contains a valid Zilliz Cloud API key (not a cluster connection string). Generate one under Settings > API Keys in the Zilliz Cloud console.
uvx cannot find the zilliz-mcp-server package
Update uv with `uv self update` and try again. If the package is not yet on PyPI, clone the repository and run `uv run src/zilliz_mcp_server/server.py` directly.
HTTP mode returns connection refused when client tries to connect
Ensure the server is running on port 8000 and the client URL is set to `http://localhost:8000/mcp`. Check that no firewall rule is blocking the port.
Frequently Asked Questions about Zilliz Cloud MCP
What is Zilliz Cloud MCP?
Zilliz Cloud MCP is a Model Context Protocol (MCP) server that model context protocol (mcp) server seamlessly connecting ai agents and ai coding tools with zilliz cloud https://zilliz.com/ It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Zilliz Cloud MCP?
Follow the installation instructions on the Zilliz Cloud MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Zilliz Cloud MCP?
Zilliz Cloud MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Zilliz Cloud MCP free to use?
Yes, Zilliz Cloud MCP is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Zilliz Cloud MCP Alternatives — Similar Databases Servers
Looking for alternatives to Zilliz Cloud MCP? 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 Zilliz Cloud MCP 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 Zilliz Cloud MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.