zilliz-mcp-server

zilliz-mcp-server

3.4

If you are the rightful owner of zilliz-mcp-server 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.

Zilliz-MCP-Server is a Model Context Protocol server that integrates AI applications with Milvus and Zilliz Cloud for seamless vector database management.

Zilliz-MCP-Server is a robust Model Context Protocol (MCP) server designed to facilitate seamless interaction between AI agents and vector databases like Milvus and Zilliz Cloud. By acting as a universal interface, it allows AI applications to securely connect to external data sources and tools in real-time. This integration enables AI assistants to perform tasks such as creating collections, inserting vector data, and conducting semantic searches directly within their conversations, eliminating the need for manual database management. The server is compatible with popular AI-powered coding tools like Cursor, Claude, and Windsurf, allowing developers to build vector search capabilities directly within their development workflow. With Zilliz-MCP-Server, users can create and manage vector database clusters, monitor performance, and perform semantic searches using natural language, making it an invaluable tool for developers and data scientists working with AI and vector databases.

Features

  • Seamless integration with Milvus and Zilliz Cloud for vector database management.
  • Real-time connection to external data sources and tools.
  • Compatibility with popular AI-powered coding tools like Cursor, Claude, and Windsurf.
  • Natural language interface for creating clusters, monitoring performance, and performing searches.
  • Elimination of manual database management tasks.

Tools

  1. list_projects

    List all projects in your Zilliz Cloud account.

  2. list_clusters

    List all clusters within your projects.

  3. create_free_cluster

    Create a new, free-tier Milvus cluster.

  4. describe_cluster

    Get detailed information about a specific cluster.

  5. suspend_cluster

    Suspend a running cluster to save costs.

  6. resume_cluster

    Resume a suspended cluster.

  7. query_cluster_metrics

    Query various performance metrics for a cluster.

  8. list_databases

    List all databases within a specific cluster.

  9. list_collections

    List all collections within a database.

  10. create_collection

    Create a new collection with a specified schema.

  11. describe_collection

    Get detailed information about a collection, including its schema.

  12. insert_entities

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

  13. delete_entities

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

  14. search

    Perform a vector similarity search on a collection.

  15. query

    Query entities based on a scalar filter expression.

  16. hybrid_search

    Perform a hybrid search combining vector similarity and scalar filters.