database
Qdrant CLI for Headless Automation
Use the Qdrant CLI for headless automation with headless JSON commands, schema discovery, credentials, and permission controls.
6 functions 4 read 2 write API key auth
Qdrant CLI for Headless Automation
Use KosmoKrator as a non-interactive integration runtime for local automations and wrappers.
Use headless automation when another tool needs a stable local command surface. The Qdrant CLI uses the same integration registry as the TUI, Lua runtime, and MCP gateway, but returns predictable command output for automation.
Command Shape
# Qdrant CLI for Headless Automation
kosmokrator integrations:configure qdrant --set api_key="$QDRANT_API_KEY" --enable --read allow --write ask --json
kosmo integrations:call qdrant.qdrant_list_collections '{}' --jsonDiscovery Before Execution
Agents and scripts can inspect Qdrant docs and schemas 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 --jsonUseful Qdrant CLI Functions
| Function | Type | Parameters | Description |
|---|---|---|---|
qdrant.qdrant_list_collections | Read | none | List all vector collections in the Qdrant cluster. Returns collection names and basic metadata. |
qdrant.qdrant_get_collection | Read | name | Get detailed information about a specific Qdrant collection, including vector configuration, index status, and point count. |
qdrant.qdrant_create_collection | Write | name, vectors, hnsw_config, optimizers_config, quantization_config, replication_factor, shard_number | Create a new vector collection in Qdrant. You must specify the vector configuration (size, distance metric). Optionally provide HNSW, quantization, and optimization settings. |
qdrant.qdrant_search | Read | collection, vector, vector_name, filter, limit, offset, with_payload, with_vectors, score_threshold | Search for the closest vectors in a Qdrant collection. Supports vector similarity search with optional filtering, payload selection, and scoring. |
qdrant.qdrant_upsert_points | Write | collection, points, wait, ordering | Insert or update points (vectors with optional payloads) in a Qdrant collection. Each point requires an ID and a vector. Payloads are optional metadata. |
qdrant.qdrant_get_current_user | Read | none | Get information about the Qdrant cluster, including cluster status, node information, and the authenticated user context. |
Automation Notes
- Use
--jsonfor machine-readable output. - Keep credentials out of argv by using environment variables or stored KosmoKrator configuration.
- Configure read/write policy before unattended runs; use
--forceonly for trusted automation. - Use the MCP gateway instead when the agent needs dynamic tool discovery inside a conversation.