Qdrant MCP

Confirm the configured Qdrant instance is reachable and responding. Never raises to the caller: a health check that raises on the exact condition it exists to detect defeats its own purpose. Connection failures are logged and reported in the result's ok/error fields instead, so a client renders them without a tool-call error round-trip.

No parameter schema on file.

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 creat

List every collection name in the configured Qdrant instance. Example: {}

No parameter schema on file.

Return full config and status of one collection. Fails with a clear error if the collection doesn't exist. Example: {"collection_name": "docs"}

Update optimizer/HNSW/collection/vector params on an existing collection. Only the fields you pass are changed; omitted ones keep their current value. quantization_config="disabled" turns quantization off. vectors_config/sparse_vectors_config only adjust named vectors that already exist (HNSW/quantization/index tuning) — they cannot add a

Delete a collection and all its points; a no-op if it doesn't exist. Example: {"collection_name": "docs"}

Check whether a collection exists, without raising if it doesn't. Example: {"collection_name": "docs"}

Insert or replace points (id + vector + payload) in a collection. vector matches the collection's vector config: a plain list for a single unnamed vector; a list of lists for an unnamed multivector; or a dict keyed by vector name for named vectors, where each value is a dense list, a multivector, or a sparse vector ({"indices": [...], "values": [...]}).

Retrieve points by id; unknown ids are simply omitted, not an error. Fails only if the collection itself doesn't exist. Example: {"collection_name": "docs", "ids": [1, 2]}

Delete points by id list or by payload filter — exactly one of the two. Deleting an id that doesn't exist is not an error (Qdrant treats it as a no-op); this only fails if the collection itself is missing, or if you provide zero or both selectors. Example (by id): {"collection_name": "docs", "ids": [1, 2]} Example (by filter): {"collection_name": "docs", "

Page through all points in a collection, optionally filtered. Pass the returned next_page_offset as offset to fetch the next page; null means there are no more pages. limit is capped per call by the server's QDRANT_MCP_MAX_LIMIT (1000 by default). order_by sorts by a payload field instead of by id: a key, or `{"key": ..., "direction": "asc"|"desc

Count points in a collection, optionally matching a filter. Example: {"collection_name": "docs"}

Search a collection with Qdrant's unified Query API: vector similarity, hybrid fusion, multi-stage reranking, MMR diversity, payload-based score formulas, ordering by a payload field, or random sampling. Exactly one query mode is required: - query_vector — nearest points to a dense vector, a multivector (list of vectors), a sparse vector (`{"ind

Run multiple independent queries against one collection in a single round trip — each item takes every query mode and tuning parameter of qdrant_query (plain vector, fusion over prefetch, MMR, formula, order_by, sample, search_params, score_threshold, offset); timeout_seconds and consistency apply to the whole batch. Example: {"collection_name": "docs

Vector query grouped by a payload field, up to group_size hits per group — e.g. the best-matching chunks per source document. Takes every query mode and tuning parameter of qdrant_query except offset (groups have no paging). Example: {"collection_name": "docs", "group_by": "document_id", "query_vector": [0.1, 0.2, 0.3, 0.4], "group_size": 2}

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. Examples may be dense, multi- or sparse vectors, matching using. Takes the same tuning parameters as `qdrant

Run multiple independent recommend queries against one collection in a single round trip. Each item takes the tuning parameters of qdrant_recommend; timeout_seconds and consistency apply to the whole batch. Example: {"collection_name": "docs", "requests": [ {"positive": [1], "negative": [7]}, {"positive": [2, 3]} ]}

Recommend query grouped by a payload field, up to group_size hits per group. Takes the tuning parameters of qdrant_recommend except offset (groups have no paging). Example: {"collection_name": "docs", "group_by": "document_id", "positive": [1, 2], "group_size": 2}

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. The target and context may be dense, multi- or sparse vectors, matching using. Takes the same tuning parameters as qdrant_query: search_params, score_threshold, offset, `time

Run multiple independent discover queries against one collection in a single round trip. Each item takes the tuning parameters of qdrant_discover; timeout_seconds and consistency apply to the whole batch. Example: {"collection_name": "docs", "requests": [ {"target": 1, "context": [{"positive": 2, "negative": 7}]} ]}

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. Example: {"collection_name": "docs", "sample": 20, "limit": 5}

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. Example: {"collection_name": "docs", "sample": 20, "limit": 5}

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. Example: {"collection_name": "docs", "ids": [1], "payload": {"city": "ny"}}

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. Example: {"collection_name": "docs", "ids": [1], "payload": {"city": "ny"}}

Delete specific payload keys from selected points — exactly one of ids/points_filter. Other keys are untouched. Example: {"collection_name": "docs", "ids": [1], "keys": ["city"]}

Wipe the entire payload of selected points, keeping their vectors — exactly one of ids/points_filter. Example: {"collection_name": "docs", "ids": [1]}

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. Example: {"collection_name": "docs", "key": "city", "limit": 20}

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). Example: {"collection_name": "docs", "field_name": "

Delete the payload index on field_name. Example: {"collection_name": "docs", "field_name": "city"}

Add a new named vector (dense or sparse) to a collection that already has points, without touching them. Requires a recent Qdrant server: verified hands-on that this 404s on v1.13.6 and v1.15.1, and works on v1.19.0 (this project's CI floor from Fase 3 onward) — pin your server accordingly. For vector_kind="dense", give both size and distance (optiona

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. Example: {"collection_name": "docs", "vector_name": "sparse"}

Run multiple point operations (upsert, delete, set/overwrite/delete/clear payload, update/delete vectors) against one collection, in the order given, in a single request. Each item is one of Qdrant's own tagged operation shapes, keyed by operation name. Not all-or-nothing (verified): if one operation fails, the ones before it stay applied, so check the coll

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. Example: {"collection_name": "docs", "points": [ {"id": 1, "vector": [0.1, 0.2, 0.3, 0.4]} ]}

Remove specific named vectors from selected points, keeping their payload and other vectors — exactly one of ids/points_filter. Example: {"collection_name": "docs", "vector_names": ["sparse"], "ids": [1]}

List every alias on the server with the collection it points to. An alias is an alternative name for a collection, accepted by Qdrant anywhere a collection_name is — see qdrant_alias_update. Aliases are not returned by qdrant_collection_list. Example: {}

No parameter schema on file.

List the aliases that point to one collection (an empty list if it has none). Fails with a clear error if the collection doesn't exist. Example: {"collection_name": "docs_v2"}

Create, rename, re-point or delete aliases — the basis of a zero-downtime reindex: build the new collection, then switch the alias that clients use. Each operation is exactly one of create_alias (collection_name, alias_name), rename_alias (old_alias_name, new_alias_name) or delete_alias (alias_name). Operations run in order in one re

Shard layout of a collection: how many shards it has and, for each local shard, its point count and replica state. Works on a single-node deployment too (one peer, remote_shards empty); shard transfers and resharding only ever appear on a distributed deployment. Fails with a clear error if the collection doesn't exist. Example: {"collection_name": "docs"}

Progress of the background optimizer for a collection — answers "has it finished indexing?" and "why isn't the collection green?". Always returns a summary (queued optimizations/segments/points and idle segments) and the optimizations running right now. include adds detail lists: queued (waiting optimizations), completed (finished ones; bound them wit

Copy points (all vectors — dense, sparse and multivector — and payload) from one collection to another of the same Qdrant instance, entirely server-side: the vectors never pass through the model. The target must already exist with a compatible vector configuration (see qdrant_collection_info); this tool does not create it. Use it to re-create a collection

Profile the payload keys that actually occur in a collection, so filters can be written against real keys instead of guessed ones. Looks at a random sample of sample_size points (optionally limited by sample_filter) and reports, per key: the value types seen (string, integer, float, boolean, null), whether it was ever an array, how many sample

Create a snapshot of one collection's current state. Example: {"collection_name": "docs"}

List the snapshots stored for one collection. Example: {"collection_name": "docs"}

Delete a collection snapshot, freeing its disk space on the server — does not touch the live collection. Example: {"collection_name": "docs", "snapshot_name": "docs-....snapshot"}

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. location must be reachable by the Qdrant server itself, not necessarily by whoever calls this tool: an HTTP(S) URL (e.g. from qdrant_snapshot_download) or a file:// path on the server's own

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. Example: {"collection_name": "docs", "snapshot_name": "docs-....snapshot"}

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

No parameter schema on file.

List the full-storage snapshots stored on the server. Example: {}

No parameter schema on file.

Delete a full-storage snapshot, freeing its disk space. Example: {"snapshot_name": "full-....snapshot"}

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. There is no qdrant_storage_snapshot_recover: restoring a full storage snapshot is done with the server stopped, pointed at the snapshot file at startup — not a live API call. Example: {

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

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. Example: {}

No parameter schema on file.

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

No parameter schema on file.

Update server-wide resource quotas. Only the fields you pass are changed; omitted ones keep their current value. Example: {"enabled": true, "max_resident_memory_percent": 90}

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. Example: {}

No parameter schema on file.

Clear all accumulated issues. Example: {}

No parameter schema on file.