MCP For Claude Marketplace
Milvus (Open-Source Vector Database)

Milvus (Open-Source Vector Database) MCP Connector for Claude

A+

Manage vector storage via Milvus — perform ANN searches, query scalar entities, and audit collections.

7 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect your Milvus instance to any AI agent and take full control of your high-performance vector search, embedding storage, and scalar data management through natural conversation.

What you can do

  • Vector Search Orchestration — Execute Approximate Nearest Neighbor (ANN) searches against your collections by providing raw embedding vectors to retrieve semantically relevant matches directly from your agent
  • Scalar Query Filters — Use sophisticated scalar expressions to filter entities by structured fields (e.g., tags, IDs, dates) alongside your vector search for precise data retrieval
  • Collection Lifecycle Audit — List all managed vector collections and retrieve detailed schema definitions, including dimensions, primary keys, and index types natively
  • Performance Statistics — Extract real-time metrics for your collections, including entity counts and physical memory usage, to monitor the health of your vector store
  • Precision Retrieval — Fetch specific vector items by their primary keys, bypassing standard semantic boundaries to audit exact data points securely
  • Data Management — Irreversibly delete specific vector records using primary identifiers to maintain a clean and optimized search index across your Milvus instance

How it works

  1. Subscribe to this server
  2. Enter your Milvus Base URL and API Key (or Zilliz Cloud Token)
  3. Start optimizing your vector search from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • ML Engineers — test vector relevance and verify embedding dimensions through natural conversation without manual SDK scripts
  • Search Architects — audit collection schemas and monitor indexing performance directly from your workspace
  • Software Developers — integrate AI-powered retrieval into applications and manage vector lifecycles across multiple Milvus environments efficiently
vector-searchembeddingssimilarity-searchai-infrastructuredata-retrieval

7 tools expose this connector's capabilities to your AI agent.

list_collections

Always query this first. List index collections tracked inside the Milvus Vector Database

describe_collection

Explore the explicit schema mapping and indexing definition of a Milvus collection

get_collection_stats

Get collection statistics bounding row counts natively

search_vectors

Make sure to feed a strict explicit JSON Array matching exact dimensions. Search nearest vector neighbors matching implicit embedding inputs

query_entities

Query explicitly using scalar expressions to retrieve entities

get_entities

Extract unique vector items bounding exactly by known Primary Keys

delete_entities

Irreversibly delete specific vector records utilizing primary keys

See how to talk to your AI agent using Milvus (Open-Source Vector Database).

List all vector collections in my Milvus instance

I've retrieved 3 collections from your Milvus instance: 'image_embeddings' (Dim: 512), 'text_knowledge_base' (Dim: 1536), and 'user_profiles' (Dim: 768). Which one would you like to check the stats or schema for?

Search collection 'text_knowledge_base' for vector: [0.1, -0.2, ...]

Executing ANN search… I've identified the 5 nearest neighbors. The top match has a similarity score of 0.94 and maps to entity ID '12345'. Other results include related technical documentation fragments. Would you like the full scalar data for these entities?

Show me the row count and memory stats for collection 'image_embeddings'

Retrieving stats… The 'image_embeddings' collection contains 1,250,000 entities. It is currently occupying approximately 2.4 GB of memory. All indices are loaded and healthy. No anomalous data distribution detected.

Use the `search_vectors` tool by providing the collection name and a JSON float array matching the collection's dimensions. Your agent will perform an Approximate Nearest Neighbor search and return the most semantically relevant entities.

Related Connectors

OP

OpenNode MCP

22 tools Official

Process Bitcoin and Lightning Network payments, manage charges, and initiate secure withdrawals directly from your AI agent.

A+ View details →
SE

SecurityTrails MCP

10 tools Official

Uncover IT infrastructure — access DNS history, subdomains, reverse IP lookups, WHOIS data and advanced domain intelligence for ultimate OSINT.

A+ View details →
WO

WordPress MCP

7 tools Official

Build and manage websites with the CMS that powers over 40 percent of the web through posts, pages, plugins, and themes.

A+ View details →
CD

Cloud DNS (Anycast DNS Provider API) MCP

7 tools Official

Manage your Anycast DNS infrastructure — list zones, configure records, and automate domain management directly through AI.

A+ View details →