Integration

Milvus integration

Milvus and Zilliz Cloud vector database over the RESTful v2 API: create and describe collections, load and release them into memory, insert, upsert, delete and fetch entities, run vector similarity search and scalar filter queries, manage partitions, and build or drop vector indexes. Every call targets one cluster endpoint and authenticates with a cluster token.

Connect Milvus How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Milvus.Built from the 18 Milvus tools below, on the connection you add once.

Common Milvus use cases

cleaning up a test collection
checking how many vectors are indexed
loading embeddings into a vector store
listing every vector belonging to one tenant
re-indexing documents that may already exist
waiting until an index has finished building
rebuilding an index with different parameters
making a freshly created collection searchable
bootstrapping a vector store for a RAG pipeline
isolating one tenant inside a shared collection

What you can do with Milvus

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Collection, 7 operations

create_collectionCreate collectionPOSTCreates a Milvus collection for vectors.
describe_collectionDescribe collectionPOSTDescribes the schema and indexes of a Milvus collection.
drop_collectionDrop collectionPOSTPermanently deletes a Milvus collection.
get_collection_statsGet collection statsPOSTReturns the entity count of a Milvus collection.
list_collectionsList collectionsPOSTLists all collection names in a Milvus database.
load_collectionLoad collectionPOSTLoads a Milvus collection into memory for querying.
release_collectionRelease collectionPOSTReleases a Milvus collection from memory.

Entity, 6 operations

delete_entitiesDelete entitiesPOSTDeletes Milvus entities matching a filter expression.
get_entitiesGet entitiesPOSTFetches Milvus entities by their primary keys.
insert_entitiesInsert entitiesPOSTInserts vectors and their metadata into a Milvus collection.
query_entitiesQuery entitiesPOSTFetches entities matching a scalar filter expression in Milvus.
search_entitiesSearch entitiesPOSTFinds the entities whose vectors are closest to a query vector.
upsert_entitiesUpsert entitiesPOSTInserts or replaces entities by primary key in Milvus.

Index, 3 operations

create_indexCreate indexPOSTBuilds a vector or scalar index on a Milvus collection.
describe_indexDescribe indexPOSTReturns the state and build progress of a Milvus index.
drop_indexDrop indexPOSTDeletes an index from a Milvus collection.

Partition, 2 operations

create_partitionCreate partitionPOSTCreates a partition in a Milvus collection.
list_partitionsList partitionsPOSTLists the partitions of a Milvus collection.

Use Milvus from Claude Code, Cursor or Codex

Connect Milvus in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Milvus operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Milvus

Create your workspace
Sign up free. Nothing to install.
Connect Milvus once
Add your Milvus connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Milvus integration FAQ

What can you do with the Milvus integration?

LiveContext exposes 18 operations on Milvus, covering collection, entity, index and partition. Common uses include cleaning up a test collection, checking how many vectors are indexed and loading embeddings into a vector store.