Zilliz

Zilliz MCP Server lets your AI agents securely connect to Milvus vector data and Zilliz Cloud, enabling real-time vector creation, insertion, and semantic search directly within conversations. It integrates with MCP-enabled editors and coding tools so you can manage and query your vector data without leaving your AI workspace.

How to use

Use the server by connecting an MCP client in your development environment. You can run the server locally and connect via standard I/O or run it as a standalone HTTP service for remote clients. Once connected, you can create Milvus collections, insert vector data, perform semantic searches, and monitor cluster metrics—all through natural conversation or simple tool calls within your MCP-enabled workflow.

How to install

Prerequisites you need to satisfy before running the server:

• Python 3.10 or higher

Step-by-step setup

Follow these steps to install and start the MCP server in two common modes.

Standard I/O (StdIO) setup

{
  "mcpServers": {
    "zilliz-mcp-server": {
      "command": "uvx",
      "args": ["zilliz-mcp-server"],
      "env": {
          "ZILLIZ_CLOUD_TOKEN": "your-token-here"
      }
    }
  }
}

Streamable HTTP setup

Run the server as a standalone HTTP service and connect a client over HTTP.

# Start the MCP server in streamable-http mode
uv run src/zilliz_mcp_server/server.py --transport streamable-http

Configure your MCP client to connect to the HTTP endpoint shown after starting. The following example shows how you would reference the endpoint in a client configuration.

Available tools

list_projects

List all projects in your Zilliz Cloud account.

list_clusters

List all clusters within your projects.

create_free_cluster

Create a new, free-tier Milvus cluster.

describe_cluster

Get detailed information about a specific cluster.

suspend_cluster

Suspend a running cluster to save costs.

resume_cluster

Resume a suspended cluster.

query_cluster_metrics

Query various performance metrics for a cluster.

list_databases

List all databases within a specific cluster.

list_collections

List all collections within a database.

create_collection

Create a new collection with a specified schema.

describe_collection

Get detailed information about a collection, including its schema.

insert_entities

Insert entities (data records with vectors) into a collection.

delete_entities

Delete entities from a collection based on IDs or a filter expression.

search

Perform a vector similarity search on a collection.

query

Query entities based on a scalar filter expression.

hybrid_search

Perform a hybrid search combining vector similarity and scalar filters.