Platform
Platform Overview Maps Memory Shadow Mode Widget Governance Actions Integrations
Developers
Overview Catalog Guardrails Dry Run Idempotency Credentials Audit Trail API Reference
Company
About Blog Contact Book a Demo
MCP Integrations Qdrant
MCP & AI Agent Integration

Qdrant
automation.

11 automated actions available through Cerebral OS. Connect Qdrant to any workflow, Cerebral, or Map — with full governance, audit trail, and dry-run safety on every execution.

Start free — 1,000 runs Browse all integrations →

No credit card required · 1,000 free runs · 11 actions available

Execution trace
live
11
actions
100%
governed
<200ms
latency
11
Automated actions
5
Read operations
6
Write operations
2,800+
Compatible Maps
Actions

What you can do
with Qdrant.

Every action below is available as an MCP tool and a verb in Cerebral OS — callable from any AI agent, Claude, Cursor, Windsurf, or your own runtime via the BYOA API. All executions are governed, audited, and dry-run safe.

Count Points
qdrant:count_points
Count the number of points in a collection with optional filtering.
Read Low risk
Create Collection
qdrant:create_collection
Create a new vector collection with specified configuration.
Write Medium risk
Delete Collection
qdrant:delete_collection
Delete a collection and all its vectors permanently.
Write High risk
Delete Points
qdrant:delete_points
Delete specific points from a collection by their IDs.
Write High risk
Get Collection
qdrant:get_collection
Get detailed information about a specific collection.
Read Low risk
Get Point
qdrant:get_point
Retrieve a specific point by ID from a collection.
Read Low risk
List Collections
qdrant:list_collections
List all collections in the Qdrant instance.
Read Low risk
Recommend Points
qdrant:recommend_points
Get recommendations based on positive and negative examples.
Write Medium risk
Scroll Points
qdrant:scroll_points
Scroll through points in a collection with optional filtering.
Write Medium risk
Search Points
qdrant:search_points
Search for similar vectors in a collection using semantic similarity.
Read Low risk
Upsert Points
qdrant:upsert_points
Insert or update points (vectors with metadata) in a collection.
Write Medium risk
How it works

Every Qdrant action
governed end-to-end.

Cerebral OS isn't a connector. It's the execution layer that sits in front of Qdrant — adding governance, dry-run safety, and a full audit trail to every operation.

Governance first
Every verb carries a risk classification. High-risk writes require explicit approval gates before they execute in production.
Dry-run safe
Simulate any Qdrant action before it touches production. See exactly what would happen before a single real call is made.
Immutable audit trail
Every Qdrant action is logged — what ran, what changed, who approved it, when it happened. Full history on every verb, forever.
Qdrant integration

Start free.
No credit card required.

Start free with 1,000 runs — no credit card required. Connect Qdrant in minutes, dry-run every action before it touches production, full audit trail on everything.

Start free — 1,000 runs Browse all integrations →