Zilliz Cloud

Zilliz Cloud MCP Connector for Claude

A+

Manage vector collections and perform similarity searches via Zilliz Cloud.

10 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your Zilliz Cloud cluster to any AI agent to automate your vector database operations. This MCP server enables your agent to manage collections, insert data, and perform high-performance similarity searches directly from natural language.

What you can do

  • Collection Management — List, describe, create, and drop vector collections in your cluster
  • Memory Control — Load and release collections to optimize cluster resource usage and search availability
  • Vector Search — Execute complex vector similarity searches (ANN) using customizable metrics and parameters
  • Metadata Querying — Query entities using boolean expressions and metadata filters to find specific records
  • Data Maintenance — Insert new vector/scalar data and delete entities from your collections

How it works

  1. Subscribe to this server
  2. Enter your Zilliz Cluster Endpoint and API Key
  3. Start managing your vector data from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • AI Engineers — Quickly test vector searches and verify collection schemas via natural language
  • Data Scientists — Monitor cluster health and data distribution without writing boilerplate code
  • Developers — Integrate vector database management and retrieval into your development workflow
similarity-searchvector-embeddingsai-infrastructuredata-indexingcollection-managementmilvus

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

list_collections

List all collections in the Zilliz cluster

create_collection

Requires a JSON body. Create a new vector collection

delete_entities

Delete entities from a collection

describe_collection

Get details for a specific collection

drop_collection

Drop a collection

insert_entities

Insert data into a collection

load_collection

Load a collection into memory

query_entities

Query entities using metadata filtering

release_collection

Release a collection from memory

search_vectors

Requires a JSON search configuration. Perform a vector similarity search

See how to talk to your AI agent using Zilliz Cloud.

List all vector collections in my Zilliz cluster.

I've retrieved your collections. You have 3 collections: 'image_embeddings', 'text_docs', and 'product_features'. Would you like more details on any of them?

Show the schema and status for collection 'text_docs'.

Collection 'text_docs' is currently 'LOADED' with 150,000 rows. It has 3 fields: 'id' (Primary), 'vector' (FloatVector, 1536 dim), and 'metadata' (JSON).

Drop the collection named 'old_data_backup'.

Successfully dropped the collection 'old_data_backup'. All associated data has been permanently removed from your cluster.

You can find your Cluster Endpoint in the Zilliz Cloud Console under the 'Cluster Details' page. It typically looks like `https://in01-xxxxxxxxxxxx.vectordb.zillizcloud.com`.

Related Connectors