Qdrant MCP

Confirm the configured Qdrant instance is reachable and responding.

Create a collection: either a single unnamed vector (`vector_size` + `distance`), or one or more named vectors (`vectors`, each a full `VectorParams` — size, distance, and optionally its own `multivector_config` for ColBERT-style multi-vectors or `quantization_config`) — exactly one of the two. `sparse_vectors` defines sparse (keyword-style) vectors at creation time. `quantization_config` (scalar/product/binary) and `strict_mode_config` apply to the whole collection.

List every collection name in the configured Qdrant instance.

Return full config and status of one collection.

Update optimizer/HNSW/collection/vector params on an existing collection.

Delete a collection and all its points; a no-op if it doesn't exist.

Check whether a collection exists, without raising if it doesn't.

Insert or replace points (id + vector + payload) in a collection.

Retrieve points by id; unknown ids are simply omitted, not an error.

Delete points by id list or by payload filter — exactly one of the two.

Page through all points in a collection, optionally filtered.

Count points in a collection, optionally matching a filter.

Vector similarity search, with optional hybrid search over multiple prefetch stages.

Run multiple independent queries against one collection in a single round trip — same query shapes as `qdrant_query` (plain vector or fusion+prefetch hybrid search), one per list item.

Vector query grouped by a payload field, up to `group_size` hits per group — e.g. the best-matching chunks per source document. Same query shapes as `qdrant_query`.

Find points similar to a set of positive examples and dissimilar to a set of negative ones (vectors or point ids) — Qdrant's recommendation API. Requires at least one of `positive`/`negative`; the server rejects an empty request with a clear error.

Run multiple independent recommend queries against one collection in a single round trip.

Recommend query grouped by a payload field, up to `group_size` hits per group.

Rank points by how well they fit a target within positive/negative context pairs (vectors or point ids) — Qdrant's discovery search, a finer-grained alternative to recommend.

Run multiple independent discover queries against one collection in a single round trip.

Pairwise distance matrix between a random sample of points: for each of `sample` points, its `limit` closest neighbors among that same sample — returned as a flat list of (a, b, score) pairs.

Same distance matrix as `qdrant_distance_matrix_pairs`, in a column-oriented shape (offsets into a shared id list + a parallel score array) — more compact for large samples.

Merge fields into the payload of selected points — exactly one of `ids`/`points_filter`. Existing keys not in `payload` are kept. `key` sets a nested sub-field (e.g. `"metadata.author"`) instead of merging at the payload root.

Replace the entire payload of selected points with `payload` — exactly one of `ids`/`points_filter`. Unlike `qdrant_payload_set`, existing keys not in `payload` are dropped.

Delete specific payload keys from selected points — exactly one of `ids`/`points_filter`. Other keys are untouched.

Wipe the entire payload of selected points, keeping their vectors — exactly one of `ids`/`points_filter`.

Count distinct values of a payload field across the collection (or a filtered subset) — e.g. how many points per `city`. `exact` trades speed for an exact count instead of an approximation.

Create a payload index on `field_name`, speeding up filters that use it. `field_schema` can be a simple type name ("keyword", "integer", "float", "geo", "text", "bool", "datetime", "uuid") or a detailed params object (e.g. a `text` index with a specific tokenizer, or a `keyword` index marked `is_tenant`).

Delete the payload index on `field_name`.

Add a new named vector (dense or sparse) to a collection that already has points, without touching them.

Remove a named vector (dense or sparse) from a collection — points keep their other vectors and payload. Same server-version requirement as `qdrant_collection_vector_create`.

Run multiple point operations (upsert, delete, set/overwrite/delete/clear payload, update/delete vectors) atomically against one collection, in the order given. Each item is one of Qdrant's own tagged operation shapes, keyed by operation name.

Replace the vector(s) of existing points by id — leaves their payload untouched. For a named-vector collection, `vector` is a dict keyed by vector name; for a single unnamed vector, pass a plain vector.

Remove specific named vectors from selected points, keeping their payload and other vectors — exactly one of `ids`/`points_filter`.

Create a snapshot of one collection's current state.

List the snapshots stored for one collection.

Delete a collection snapshot, freeing its disk space on the server — does not touch the live collection.

Overwrite `collection_name` with the state captured in a snapshot — everything written since that snapshot is lost. Creates the collection if it doesn't exist.

Confirm a collection snapshot exists and return where to fetch it from — this tool does not transfer the (potentially huge) snapshot file itself; download it yourself (e.g. `curl`) from the returned `url`.

Create a snapshot of the whole storage (every collection and server config), not just one collection.

List the full-storage snapshots stored on the server.

Delete a full-storage snapshot, freeing its disk space.

Confirm a full-storage snapshot exists and return where to fetch it from — same caveat as `qdrant_snapshot_download`: this tool does not transfer the file itself.

Server-wide telemetry: build info, per-collection stats, request counters, memory and hardware usage. Not tied to any one collection.

Return the URL where Qdrant serves Prometheus-format metrics — this tool does not fetch the metrics themselves (they're plain text, not JSON); point your Prometheus scraper at the returned `url` instead.

Current server-wide resource quotas (memory/disk limits) and actual usage.

Update server-wide resource quotas. Only the fields you pass are changed; omitted ones keep their current value.

List the issues Qdrant has detected about its own configuration (e.g. a heavily-filtered field with no payload index). **API Beta** in Qdrant itself — the exact shape can change without notice, so this is returned as-is rather than forced into a fixed schema.

Clear all accumulated issues.