Milvus

@danchev

Visit Server

6 months ago

A Model Context Protocol (MCP) server for agentic retrieval and semantic search over unstructured and structured data using Milvus, a high-performance vector database. This server enables large language model (LLM) applications to efficiently index, store, and retrieve vector embeddings derived from diverse data sources—such as documents, images, metadata, or logs. By leveraging Milvus, the MCP server supports similarity search and contextual retrieval, enabling intelligent access to relevant information based on natural language queries. Designed for integration with MCP-compatible clients, this solution provides a scalable, low-latency foundation for building AI-powered applications with contextual awareness and retrieval-augmented generation (RAG) capabilities.

Overview Tools Comments

Overview

Milvus

MCP server built on top of Milvus, a high-performance vector database.

Available Tools

The server provides the following tools:

Search and Query Operations

milvus_text_search: Search for documents using full text search
- Parameters:
  - collection_name: Name of collection to search
  - query_text: Text to search for
  - limit: Maximum results (default: 5)
  - output_fields: Fields to include in results
  - drop_ratio: Proportion of low-frequency terms to ignore (0.0-1.0)
milvus_vector_search: Perform vector similarity search on a collection
- Parameters:
  - collection_name: Name of collection to search
  - vector: Query vector
  - vector_field: Field containing vectors to search (default: "vector")
  - limit: Maximum results (default: 5)
  - output_fields: Fields to include in results
  - metric_type: Distance metric (COSINE, L2, IP) (default: "COSINE")
milvus_query: Query collection using filter expressions
- Parameters:
  - collection_name: Name of collection to query
  - filter_expr: Filter expression (e.g. 'age > 20')
  - output_fields: Fields to include in results
  - limit: Maximum results (default: 10)

Collection Management

milvus_list_collections: List all collections in the database
milvus_create_collection: Create a new collection with specified schema
- Parameters:
  - collection_name: Name for the new collection
  - collection_schema: Collection schema definition
  - index_params: Optional index parameters
milvus_load_collection: Load a collection into memory for search and query
- Parameters:
  - collection_name: Name of collection to load
  - replica_number: Number of replicas (default: 1)
milvus_release_collection: Release a collection from memory
- Parameters:
  - collection_name: Name of collection to release
milvus_get_collection_info: Lists detailed information like schema, properties, collection ID, and other metadata of a specific collection.
- Parameters:
  - collection_name: Name of the collection to get detailed information about

Data Operations

milvus_insert_data: Insert data into a collection
- Parameters:
  - collection_name: Name of collection
  - data: Dictionary mapping field names to lists of values
milvus_delete_entities: Delete entities from a collection based on filter expression
- Parameters:
  - collection_name: Name of collection
  - filter_expr: Filter expression to select entities to delete

Try in Playground

Server Config

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

Build with ShipAny.