Database

Qdrant

High-performance open-source vector similarity search engine designed for production-grade AI applications with advanced filtering and scalable architecture.

Qdrant MCP, Integrations & Automations for Enterprise AI Agents

Connect your AI agents to Qdrant MCP in minutes. No field mapping. No code required. Adopt AI's zero-shot API discovery means your agents understand Qdrant's schema on first contact - and can act on it instantly.

Generate MCP URL

What Your AI Agents Can Do

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Move Shard on Qdrant

Initiates shard movement POST /collections/{collection_name}/cluster/move_shard. Returns async operation status. Use during cluster rebalancing.

Create Alias on Qdrant

Creates a collection alias POST /collections/aliases. Returns status. Use for zero-downtime reindex with QD_SWITCH_ALIAS.

Create Collection on Qdrant

Creates a collection with PUT /collections/{collection_name} and vectors size/distance JSON. Returns acknowledgment. Use QD_CREATE_COLLECTION_AND_WAIT for wait=true.

Query on Qdrant

Universal query API POST .../points/query combining nearest/recommend/discover modes per body. Returns mode-specific results. Use when experimenting; prefer specialized tools for fixed workflows.

Get Point on Qdrant

GET single point /collections/{collection_name}/points/{id}. Returns point detail. Use for spot checks; bulk reads use QD_GET_POINTS.

Switch Alias on Qdrant

Atomically retargets an alias PUT /collections/aliases (action: rename/swap per Qdrant). Supply body JSON per API. Use for zero-downtime reindex cutover.

Delete Collection on Qdrant

Deletes a collection via DELETE /collections/{collection_name}. Returns true when removed. Irreversible; export snapshots first with QD_CREATE_SNAPSHOT.

Upsert Points And Wait on Qdrant

Same as QD_UPSERT_POINTS but always passes wait=true so Qdrant acknowledges persistence before returning. Use when downstream search must see writes immediately.

Query Batch on Qdrant

Batch universal queries POST .../points/query/batch. Returns multiple result sets. Use for throughput; mirrors QD_QUERY semantics.

Get Info on Qdrant

Returns version, title, and commit from GET /. Use to verify connectivity before heavy operations. Prefer QD_HEALTH_CHECK for load-balancer probes.

Get Telemetry on Qdrant

Reads anonymized telemetry JSON from GET /telemetry when enabled. Returns usage counters. Use for support bundles; disable telemetry if policy forbids.

Create Collection And Wait on Qdrant

Creates collection then polls GET /collections/{name} until status is green or timeout. Returns last describe. Use in automation; interactive flows can use QD_CREATE_COLLECTION only.

Search Groups on Qdrant

Grouped search POST /collections/{collection_name}/points/search/groups to deduplicate by a payload key. Returns group leaders per group_id. Use for catalog dedup RAG; flat lists use QD_SEARCH.

Count Points on Qdrant

Counts points matching filter POST /collections/{collection_name}/points/count. Returns count. Use before expensive deletes; exact totals may depend on indexing.

Create Snapshot on Qdrant

Creates a snapshot POST /collections/{collection_name}/snapshots. Returns snapshot name/path. Use for backups; list with QD_LIST_SNAPSHOTS.

Search Simple on Qdrant

Shortcut search: only collection_name, query_vector JSON array, and limit (default 10). Returns hits with payload. Use when no filter is needed; filters belong in QD_SEARCH_WITH_FILTER.

Discover Batch on Qdrant

Batch discovery POST /collections/{collection_name}/points/discover/batch for multiple context sets. Returns grouped discovery results. Use for exploratory UIs at scale; single calls use QD_DISCOVER.

Recommend on Qdrant

Recommends using positive/negative example ids POST .../points/recommend. Returns similar points. Use for “more like this”; vector queries use QD_SEARCH.

Search With Filter on Qdrant

Example-first search: supply collection_name, query_vector JSON, and filter JSON (Qdrant Filter object). Returns filtered neighbors. Use for metadata gating; free-form filters still supported via QD_SEARCH body.

Get Shard Info on Qdrant

Shard transfer info GET /collections/{collection_name}/cluster. Returns shard layout. Use before QD_MOVE_SHARD operations.

Delete Point Payload on Qdrant

Deletes payload keys POST /collections/{collection_name}/points/payload/delete. Returns status. Use to strip fields; for full point removal use QD_DELETE_POINTS.

Search Batch on Qdrant

Runs multiple searches in one POST .../points/search/batch. Returns array aligned to requests. Use for multi-query RAG; single query should use QD_SEARCH.

List Cluster Peers on Qdrant

Lists peers GET /cluster/peers. Returns URIs and ids. Use before QD_REMOVE_PEER maintenance.

Get Points on Qdrant

Retrieves points by ids POST /collections/{collection_name}/points. Returns vectors and payloads. Use when ids are known; listing unknown ids uses QD_SCROLL_POINTS.

Delete Payload Index on Qdrant

Deletes a payload index DELETE /collections/{collection_name}/index/{field_name}. Returns status. Use to drop unused indexes and save memory.

Delete Points on Qdrant

Deletes points by filter or ids POST /collections/{collection_name}/points/delete. Returns status. Use surgical cleanup; bulk scans may prefer QD_SCROLL_POINTS first.

Get Cluster Info on Qdrant

Cluster metadata GET /cluster. Returns peers and raft info when clustering enabled. Use on self-hosted clusters; single nodes return minimal data.

List Collections on Qdrant

Lists collections with GET /collections and optional offset/limit pagination. Returns names and basic info. Use before QD_GET_COLLECTION.

Batch Update on Qdrant

Applies multiple upserts/deletes in one POST /collections/{collection_name}/points/batch. Returns per-operation results. Use for throughput; simpler single ops use QD_UPSERT_POINTS.

Search on Qdrant

Vector search POST /collections/{collection_name}/points/search with vector, limit, filter, with_payload, with_vector, params. Returns scored hits. Example filter: {"must":}.

Search Intent Top5 on Qdrant

Shortcut: QD_SEARCH with merged body default limit 5 and with_payload true. Returns top five neighbors. Use for tight RAG windows; increase via QD_SEARCH.

Scroll Points on Qdrant

Scrolls points POST /collections/{collection_name}/points/scroll with optional filter and offset/limit for full scans. Returns next_page_offset. Paginate until null.

Get Collection on Qdrant

Describes vectors config, points count, and status via GET /collections/{collection_name}. Use before searches; use QD_LIST_COLLECTIONS to discover names.

Get Metrics on Qdrant

Exports Prometheus metrics from GET /metrics. Returns plain text exposition format. Use for monitoring; not JSON—parse with metrics tooling.

Search Intent Metadata Only on Qdrant

Shortcut: search with with_vector false to trim bandwidth. Returns ids, scores, payloads. Use in production RAG; enable vectors in QD_SEARCH when debugging embeddings.

Search By Payload on Qdrant

Scroll-style browse: POST /collections/{collection_name}/points/scroll with filter only (no vector) via body JSON. Returns points matching payload constraints. Use for admin exports; similarity needs QD_SEARCH.

Update Collection on Qdrant

Patches optimizers, HNSW, or quantization via PATCH /collections/{collection_name}. Returns status. Use for tuning; destructive deletes use QD_DELETE_COLLECTION.

Update Point Payload on Qdrant

Sets or merges payload fields POST /collections/{collection_name}/points/payload. Returns status. Use for metadata updates without changing vectors.

Discover on Qdrant

Discovery search with context pairs POST .../points/discover. Returns exploratory neighbors. Use for exploratory UI; standard kNN remains QD_SEARCH.

Upsert Points on Qdrant

Upserts points PUT /collections/{collection_name}/points?wait=true|false with points array. Returns operation status. Use QD_UPSERT_POINTS_AND_WAIT for wait forced true.

Remove Peer on Qdrant

Removes a peer POST /cluster/peers/remove with body {peer_id}. Returns status. Destructive—use only during controlled downsizing.

List Indexes on Qdrant

Lists payload indexes GET /collections/{collection_name}/index. Returns indexed fields. Use before QD_CREATE_PAYLOAD_INDEX to avoid duplicates.

Create Payload Index on Qdrant

Creates payload index PUT /collections/{collection_name}/index for keyword/integer/float/geo/text fields. Returns status. Improves filter speed; unnecessary for tiny collections.

Health Check on Qdrant

Liveness probe via GET /healthz. Returns ok when process is up. Use for orchestration; pair with QD_GET_TELEMETRY for diagnostics.

Recommend Batch on Qdrant

Batch recommend POST .../points/recommend/batch. Returns grouped results. Use for catalog personalization at scale.

List Snapshots on Qdrant

Lists snapshots GET /collections/{collection_name}/snapshots. Returns snapshot metadata with pagination when available. Use before recovery operations.

Clear Point Payload on Qdrant

Clears all payload POST /collections/{collection_name}/points/payload/clear. Returns status. Use for privacy scrub; vectors remain until deleted.

List Aliases on Qdrant

Lists aliases GET /collections/aliases. Returns mapping of alias to collection. Use before QD_SWITCH_ALIAS.

Delete Alias on Qdrant

Deletes an alias via DELETE /collections/aliases/{alias_name}. Returns status. Use after cutover cleanup.

Search Intent High Recall on Qdrant

Shortcut search with default limit 50 for recall-heavy retrieval. Returns larger candidate sets. Use before reranking; not ideal for latency-sensitive chat alone.

Connect Qdrant MCP using Adopt AI in 3 Simple Steps

Run a single command in your terminal to install the Qdrant MCP server locally, no complex setup, no cloud dependency.
A browser window opens automatically, where you can securely authenticate with your Qdrant account with one click.
Restart your AI client, and your agents instantly have full access to collections, points, vectors, and every Qdrant object, ready to read, write, and automate.

Use Cases for Qdrant MCP

1. Semantic Similarity Search

AI agents query Qdrant collections to find the most similar items � documents, products, or records � enabling powerful recommendation and matching workflows.

2. RAG-Powered Knowledge Retrieval

AI agents use Qdrant as the vector store in retrieval-augmented generation pipelines, serving precise context from large document collections to LLMs in real time.

3. Anomaly & Fraud Detection

AI agents compare incoming data points against Qdrant vector collections to detect outliers, anomalous patterns, and potential fraud in transactions or user behavior.

4. Image & Media Search

AI agents store and query image embeddings in Qdrant to enable visual similarity search, content moderation, and media asset discovery at scale.

5. Dynamic Collection Management

AI agents automatically create, update, and optimize Qdrant collections as data grows, managing indexing strategies and payload filtering for peak performance.

Explore Similar Apps

Pinecone

Weaviate

Chroma

Frequently Asked Questions

Do I need my own developer credentials to use Qdrant MCP with Adopt AI?

No, you can get started immediately using Adopt AI's built-in Qdrant integration. For production use, we recommend configuring your own API credentials for greater control and security.

Can I connect Qdrant with other apps through Adopt AI?

Yes! Adopt AI supports multi-app workflows, so your AI agents can seamlessly move data between Qdrant and LLM platforms, search tools, knowledge bases, and more.

Is Adopt AI secure?

Absolutely. Adopt AI is SOC 2 Type 2 certified and ISO/IEC 27001 compliant, and adheres to EU GDPR, CCPA, and HIPAA standards. All data is encrypted in transit and at rest, ensuring the confidentiality, integrity, and availability of your data. Learn more here.

What happens if the Qdrant API changes?

Adopt AI maintains and updates all integrations automatically, so your agents always work with the latest API versions, no manual maintenance required.

Do I need coding skills to set up the Qdrant integration?

Not at all. Adopt AI's zero-shot API discovery means your agents understand Qdrant's schema on first contact. Setup takes minutes with no code required.

How do I set up custom Qdrant MCP in Adopt AI?

For a step-by-step guide on creating and configuring your own Qdrant API credentials with Adopt AI, see here.