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 MCP, CLI, and Lua Integration for AI Agents

Qdrant integration docs for AI agents: MCP gateway setup, Qdrant CLI commands, Lua API reference, credentials, and function schemas.

6 functions 4 read 2 write API key auth

Submit Qdrant feedback View package source

Qdrant for agents

Credentials can be configured manually in web or CLI hosts.

Use this integration from Lua code mode, the headless integrations CLI, or the KosmoKrator MCP gateway. The same package metadata powers all three surfaces.

Machine-Readable Metadata

integration_slug: qdrant
route_slug: qdrant
package: qdrant
auth_strategy: api_key API key
cli_setup_supported: true
cli_runtime_supported: true
mcp_gateway_supported: true
lua_supported: true
supports_multi_account: true

Quick Links

Lua APIAgent-facing namespace and function reference. Qdrant CLIHeadless setup and direct function calls. Qdrant MCPMCP gateway setup for external clients. Submit feedbackReport missing tools, auth problems, wrong docs, or runtime issues. ContributeAdd tools or improve metadata in the integrations repo.

Qdrant MCP Client Matrix

Use these pages when a specific agent client or framework needs copy-pasteable MCP setup for Qdrant.

Claude Code Qdrant MCP setup for Claude Code. Cursor Qdrant MCP setup for Cursor. Codex Qdrant MCP setup for Codex. OpenAI Agents Qdrant MCP setup for OpenAI Agents SDK. Claude Agent SDK Qdrant MCP setup for Claude Agent SDK. Vercel AI SDK Qdrant MCP setup for Vercel AI SDK. LangChain Qdrant MCP setup for LangChain. LangGraph Qdrant MCP setup for LangGraph. CrewAI Qdrant MCP setup for CrewAI. MCP clients Qdrant MCP setup for Generic MCP Clients.

Qdrant CLI Matrix

Use these pages for direct Qdrant CLI workflows in scripts, CI, cron, and agent wrappers.

CI Qdrant CLI for CI. Cron Jobs Qdrant CLI for cron jobs. Shell Scripts Qdrant CLI for shell scripts. Headless Automation Qdrant CLI for headless automation. Coding Agents Qdrant CLI for coding agents.

Function Catalog

Function	Type	Parameters	Description
`qdrant.qdrant_list_collections`	Read `read`	0	List all vector collections in the Qdrant cluster. Returns collection names and basic metadata.
`qdrant.qdrant_get_collection`	Read `read`	1	Get detailed information about a specific Qdrant collection, including vector configuration, index status, and point count.
`qdrant.qdrant_create_collection`	Write `write`	7	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 `read`	9	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 `write`	4	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 `read`	0	Get information about the Qdrant cluster, including cluster status, node information, and the authenticated user context.