Can I use Qdrant as a CLI?

Yes. KosmoKrator exposes a Qdrant CLI through kosmo integrations:call and the provider shortcut command. Commands can return JSON for scripts, CI, and coding agents.

Can I expose Qdrant through MCP?

Yes. The KosmoKrator MCP gateway can expose selected Qdrant tools to clients such as Claude Code, Cursor, Codex, and other MCP-compatible tools.

Where are Qdrant credentials stored?

Qdrant credentials are configured in KosmoKrator's local integration settings and reused by CLI, Lua, and MCP gateway surfaces.

Can I deny write access for Qdrant MCP tools?

Yes. Start the gateway with --write=deny for read-only clients, or use ask/allow only for trusted workspaces.

database

Qdrant CLI for AI Agents

Use the Qdrant CLI from KosmoKrator to call Qdrant tools headlessly, return JSON, inspect schemas, and automate workflows from coding agents, scripts, and CI.

6 functions 4 read 2 write API key auth

Submit Qdrant feedback View package source

Qdrant CLI Setup

Qdrant can be configured headlessly with `kosmokrator integrations:configure qdrant`.

# Install KosmoKrator first if it is not available on PATH.
curl -fsSL https://raw.githubusercontent.com/OpenCompanyApp/kosmokrator/main/install.sh | bash

# Configure and verify this integration.
kosmokrator integrations:configure qdrant --set api_key="$QDRANT_API_KEY" --enable --read allow --write ask --json
kosmokrator integrations:doctor qdrant --json
kosmokrator integrations:status --json

Credentials

Authentication type: API key api_key. Configure credentials once, then use the same stored profile from scripts, coding CLIs, Lua code mode, and the MCP gateway.

Key	Env var	Type	Required	Label
`api_key`	`QDRANT_API_KEY`	Secret `secret`	yes	API Key
`url`	`QDRANT_URL`	URL `url`	no	Cluster URL

Call Qdrant Headlessly

Use the generic call form when another coding CLI or script needs a stable universal interface.

kosmo integrations:call qdrant.qdrant_list_collections '{}' --json

Use the provider shortcut form for shorter human-facing commands.

kosmo integrations:qdrant qdrant_list_collections '{}' --json

Agent Discovery Commands

These commands return structured output for coding agents that need to inspect capabilities before choosing a function.

kosmo integrations:docs qdrant --json
kosmo integrations:docs qdrant.qdrant_list_collections --json
kosmo integrations:schema qdrant.qdrant_list_collections --json
kosmo integrations:search "Qdrant" --json
kosmo integrations:list --json

All CLI Functions

Every function below can be called headlessly. The generic form is stable across all integrations; the provider shortcut is shorter but specific to Qdrant.

`qdrant.qdrant_list_collections`

Read read

List all vector collections in the Qdrant cluster. Returns collection names and basic metadata.

Parameters: none

Generic CLI call

kosmo integrations:call qdrant.qdrant_list_collections '{}' --json

Provider shortcut

kosmo integrations:qdrant qdrant_list_collections '{}' --json

`qdrant.qdrant_get_collection`

Read read

Get detailed information about a specific Qdrant collection, including vector configuration, index status, and point count.

Parameters: name

Generic CLI call

kosmo integrations:call qdrant.qdrant_get_collection '{"name":"example_name"}' --json

Provider shortcut

kosmo integrations:qdrant qdrant_get_collection '{"name":"example_name"}' --json

`qdrant.qdrant_create_collection`

Write write

Create a new vector collection in Qdrant. You must specify the vector configuration (size, distance metric). Optionally provide HNSW, quantization, and optimization settings.

Parameters: name, vectors, hnsw_config, optimizers_config, quantization_config, replication_factor, shard_number

Generic CLI call

kosmo integrations:call qdrant.qdrant_create_collection '{"name":"example_name","vectors":"example_vectors","hnsw_config":"example_hnsw_config","optimizers_config":"example_optimizers_config","quantization_config":"example_quantization_config","replication_factor":1,"shard_number":1}' --json

Provider shortcut

kosmo integrations:qdrant qdrant_create_collection '{"name":"example_name","vectors":"example_vectors","hnsw_config":"example_hnsw_config","optimizers_config":"example_optimizers_config","quantization_config":"example_quantization_config","replication_factor":1,"shard_number":1}' --json

`qdrant.qdrant_search`

Read read

Search for the closest vectors in a Qdrant collection. Supports vector similarity search with optional filtering, payload selection, and scoring.

Parameters: collection, vector, vector_name, filter, limit, offset, with_payload, with_vectors, score_threshold

Generic CLI call

kosmo integrations:call qdrant.qdrant_search '{"collection":"example_collection","vector":"example_vector","vector_name":"example_vector_name","filter":"example_filter","limit":1,"offset":1,"with_payload":true,"with_vectors":true}' --json

Provider shortcut

kosmo integrations:qdrant qdrant_search '{"collection":"example_collection","vector":"example_vector","vector_name":"example_vector_name","filter":"example_filter","limit":1,"offset":1,"with_payload":true,"with_vectors":true}' --json

`qdrant.qdrant_upsert_points`

Write write

Insert or update points (vectors with optional payloads) in a Qdrant collection. Each point requires an ID and a vector. Payloads are optional metadata.

Parameters: collection, points, wait, ordering

Generic CLI call

kosmo integrations:call qdrant.qdrant_upsert_points '{"collection":"example_collection","points":"example_points","wait":true,"ordering":"example_ordering"}' --json

Provider shortcut

kosmo integrations:qdrant qdrant_upsert_points '{"collection":"example_collection","points":"example_points","wait":true,"ordering":"example_ordering"}' --json

`qdrant.qdrant_get_current_user`

Read read

Get information about the Qdrant cluster, including cluster status, node information, and the authenticated user context.

Parameters: none

Generic CLI call

kosmo integrations:call qdrant.qdrant_get_current_user '{}' --json

Provider shortcut

kosmo integrations:qdrant qdrant_get_current_user '{}' --json

Function Schemas

Use these parameter tables when building CLI payloads without calling integrations:schema first.

`qdrant.qdrant_list_collections`

List all vector collections in the Qdrant cluster. Returns collection names and basic metadata.

Operation: Read read
Schema command: kosmo integrations:schema qdrant.qdrant_list_collections --json

Parameter	Type	Required	Description
No parameters.

`qdrant.qdrant_get_collection`

Get detailed information about a specific Qdrant collection, including vector configuration, index status, and point count.

Operation: Read read
Schema command: kosmo integrations:schema qdrant.qdrant_get_collection --json

Parameter	Type	Required	Description
`name`	string	yes	The name of the collection to retrieve.

`qdrant.qdrant_create_collection`

Create a new vector collection in Qdrant. You must specify the vector configuration (size, distance metric). Optionally provide HNSW, quantization, and optimization settings.

Operation: Write write
Schema command: kosmo integrations:schema qdrant.qdrant_create_collection --json

Parameter	Type	Required	Description
`name`	string	yes	Name for the new collection.
`vectors`	object	yes	Vector configuration. Example: {"size": 1536, "distance": "Cosine"}. Distance options: Cosine, Euclid, Dot.
`hnsw_config`	object	no	HNSW index configuration (e.g., {"m": 16, "ef_construct": 100}).
`optimizers_config`	object	no	Optimizer configuration (e.g., {"indexing_threshold": 20000}).
`quantization_config`	object	no	Quantization configuration for memory savings (scalar or product).
`replication_factor`	integer	no	Number of replicas for each shard (default: 1).
`shard_number`	integer	no	Number of shards for the collection (default: 1 for single-node).

`qdrant.qdrant_search`

Search for the closest vectors in a Qdrant collection. Supports vector similarity search with optional filtering, payload selection, and scoring.

Operation: Read read
Schema command: kosmo integrations:schema qdrant.qdrant_search --json

Parameter	Type	Required	Description
`collection`	string	yes	The collection name to search in.
`vector`	array	no	The query vector (array of floats). Use this for direct vector search.
`vector_name`	string	no	Named vector to search against (for multi-vector collections).
`filter`	object	no	Filter conditions to narrow results. JSON object with "must", "should", "must_not" clauses.
`limit`	integer	no	Maximum number of results to return (default: 10).
`offset`	integer	no	Offset for pagination.
`with_payload`	boolean	no	Whether to include point payloads in results (default: true).
`with_vectors`	boolean	no	Whether to include vectors in results (default: false).
`score_threshold`	number	no	Minimum similarity score threshold. Results below this are excluded.

`qdrant.qdrant_upsert_points`

Insert or update points (vectors with optional payloads) in a Qdrant collection. Each point requires an ID and a vector. Payloads are optional metadata.

Operation: Write write
Schema command: kosmo integrations:schema qdrant.qdrant_upsert_points --json

Parameter	Type	Required	Description
`collection`	string	yes	The collection name to upsert points into.
`points`	array	yes	Array of point objects. Each point must have "id" (integer or UUID string), "vector" (array of floats), and optionally "payload" (object with metadata).
`wait`	boolean	no	Whether to wait for the operation to complete (default: true).
`ordering`	string	no	Write ordering guarantee: "weak" or "strong" (default: "weak").

`qdrant.qdrant_get_current_user`

Get information about the Qdrant cluster, including cluster status, node information, and the authenticated user context.

Operation: Read read
Schema command: kosmo integrations:schema qdrant.qdrant_get_current_user --json

Parameter	Type	Required	Description
No parameters.

Permissions

Headless calls still follow the integration read/write permission policy. Configure read/write defaults with integrations:configure. Add --force only for trusted automation that should bypass that policy.