Integration

Qdrant integration

High-performance vector database and similarity search engine. Store, search, and manage vector embeddings with payload data. Perfect for semantic search, recommendation systems, RAG applications, and AI-powered similarity matching.

Connect Qdrant How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Qdrant.Built from the 15 Qdrant tools below, on the connection you add once.

Common Qdrant use cases

Export all vectors
Get collection size
Product recommendations
Retrieve document by ID
Process multiple queries
Semantic document search
Update document metadata
Index document embeddings
Remove outdated documents
Initialize embedding store

What you can do with Qdrant

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.

Point, 8 operations

count_pointsCount pointsPOSTCounts the number of points in a collection with optional filtering.
delete_pointsDelete pointsPOSTDeletes points from a collection by IDs or filter conditions.
get_pointsGet pointsPOSTRetrieves specific points by their IDs with optional payload and vector data.
query_pointsQuery pointsPOSTUniversal query endpoint supporting vector search, recommendations, discovery, hybrid and multi-stage queries.
scroll_pointsScroll pointsPOSTIterates through all points in a collection with pagination.
search_batchSearch batchPOSTPerforms multiple similarity searches in a single request.
search_pointsSearch pointsPOSTPerforms vector similarity search to find the most similar points.
upsert_pointsUpsert pointsPUTInserts new vectors or updates existing ones with their payloads.

Collection, 4 operations

create_collectionCreate collectionPUTCreates a new collection with specified vector dimensions and distance metric.
delete_collectionDelete collectionDELETEPermanently deletes a collection and all its vectors and payloads.
get_collectionGet collectionGETRetrieves detailed information about a specific collection including configuration and statistics.
list_collectionsList collectionsGETRetrieves all vector collections in the Qdrant instance.

Index, 1 operation

create_payload_indexCreate payload indexPUTCreates an index on a payload field for faster filtering.

Payload, 1 operation

update_payloadUpdate payloadPOSTUpdates payload (metadata) for points without re-indexing vectors.

Recommendation, 1 operation

recommend_pointsRecommend pointsPOSTGenerates recommendations based on positive and negative example points.

Use Qdrant from Claude Code, Cursor or Codex

Connect Qdrant in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Qdrant 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 Qdrant

Create your workspace
Sign up free. Nothing to install.
Connect Qdrant once
Add your Qdrant 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.

Qdrant integration FAQ

What can you do with the Qdrant integration?

LiveContext exposes 15 operations on Qdrant, covering point, collection, index and payload. Common uses include Export all vectors, Get collection size and Product recommendations.