Overview

The Milvus MCP Server enables AI assistants to interact with Milvus, the high-performance open-source vector database built for scalable similarity search and AI applications. Through the Model Context Protocol, AI models can create and manage vector collections, perform semantic search, insert data, and manage indexes — making Milvus's vector storage capabilities available directly through natural language.

Official Server:

Developed by Zilliz, the team behind Milvus

Key Features

🔍

Vector Search

Perform high-dimensional vector similarity search across collections with configurable top-k results.

🗂️

Collection Management

Create, describe, list, and drop collections with custom schemas and vector dimensions.

📥

Data Ingestion

Insert vectors and associated metadata into collections for retrieval and search.

⚡

Index Management

Create and manage vector indexes to optimize search performance at scale.

🔗

Hybrid Search

Combine vector similarity with attribute filtering for precise, context-aware results.

☁️

Cloud & Self-Hosted

Connect to Milvus Lite, standalone deployments, or fully managed Zilliz Cloud clusters.

Available Tools

Quick Reference

Tool	Purpose	Category
`milvus_create_collection`	Create a new collection with quick setup or customized schema	Schema
`milvus_list_collections`	List all collections in the database	Discovery
`milvus_insert_data`	Insert data into a collection	Write
`milvus_vector_search`	Perform vector similarity search on a collection	Search
`milvus_text_search`	Search for documents using full text search	Search
`milvus_hybrid_search`	Perform hybrid search on a collection	Search
`milvus_query`	Query a collection using filter expressions	Search
`milvus_load_collection`	Load a collection into memory	Collection
`milvus_release_collection`	Release a collection from memory	Collection
`milvus_get_collection_info`	Get detailed collection information	Discovery
`milvus_delete_entities`	Delete entities based on a filter expression	Write

Detailed Usage

milvus_create_collection▶

Create a new collection with a defined schema including vector field dimension and optional metadata fields.

use_mcp_tool({
  server_name: "milvus",
   tool_name: "milvus_create_collection",
  arguments: {
    collection_name: "documents",
    dimension: 1536
  }
});

milvus_vector_search▶

Search for the most similar vectors in a collection, with optional metadata filtering.

use_mcp_tool({
  server_name: "milvus",
   tool_name: "milvus_vector_search",
  arguments: {
    collection_name: "documents",
    vector: [0.1, 0.2, ...],
    limit: 10,
    filter_expr: "category == 'research'"
  }
});

milvus_insert_data▶

Insert vectors with associated metadata into a collection for future search and retrieval.

use_mcp_tool({
  server_name: "milvus",
   tool_name: "milvus_insert_data",
  arguments: {
    collection_name: "documents",
    data: {
      id: [1, 2],
      vector: [[0.1, 0.2], [0.3, 0.4]],
      text: ["First document", "Second document"]
    }
  }
});

Installation

{
  "mcpServers": {
    "milvus": {
      "command": "uvx",
      "args": [
        "mcp-server-milvus"
      ],
      "env": {
        "MILVUS_URI": "http://localhost:19530"
      }
    }
  }
}

Connection Options:

Set MILVUS_URI to your Milvus server address. Use http://localhost:19530 for local Milvus, or your Zilliz Cloud endpoint for managed deployments. Add MILVUS_TOKEN for authentication when needed.

Common Use Cases

AI-Powered RAG Pipelines: Connect vector stores to LLMs for retrieval-augmented generation with semantic search
Document & Media Search: Index and query embeddings from documents, images, or audio for intelligent retrieval
Recommendation Systems: Build vector-based similarity search for product or content recommendations
Multi-Agent Knowledge Bases: Share a common vector store across multiple AI agents for consistent context

Sources

https://github.com/zilliztech/mcp-server-milvus

Milvus MCP Server