mcp-server-milvus

mcp-server-milvus

3.6

If you are the rightful owner of mcp-server-milvus and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

The MCP Server for Milvus enables seamless integration between LLM applications and the Milvus vector database, providing a standardized way to connect LLMs with the context they need.

The Model Context Protocol (MCP) Server for Milvus is designed to facilitate the integration of large language models (LLMs) with the Milvus vector database. This server acts as a bridge, allowing LLM applications to access and manipulate data stored in Milvus, a popular open-source vector database. The server supports various operations such as vector similarity search, hybrid search, and collection management, making it a versatile tool for applications that require advanced data retrieval capabilities. It supports two communication modes: stdio and Server-Sent Events (SSE), catering to different application needs. The server can be easily integrated with applications like Claude Desktop and Cursor, which support the MCP protocol, enabling developers to build AI-powered applications with enhanced data access and manipulation capabilities.

Features

  • Supports stdio and SSE communication modes for flexible integration.
  • Provides tools for vector similarity search, hybrid search, and collection management.
  • Easily integrates with LLM applications like Claude Desktop and Cursor.
  • Allows configuration via environment variables or command line arguments.
  • Supports debugging and inspection through the MCP Inspector tool.

Tools

  1. milvus_text_search

    Find documents using full text search

  2. milvus_vector_search

    Perform vector similarity search

  3. milvus_query

    Query collections using filter expressions

  4. milvus_list_collections

    List all collections

  5. milvus_create_collection

    Create a new collection

  6. milvus_load_collection

    Loading the collection into memory

  7. milvus_release_collection

    Free collection from memory

  8. milvus_insert_data

    Insert data into collection

  9. milvus_delete_entities

    Delete entity according to filter expression