KosmoKrator

database

Qdrant MCP Integration for OpenAI Agents SDK

Connect Qdrant to OpenAI Agents SDK through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.

6 functions 4 read 2 write API key auth
Submit Qdrant feedback View package source

Connect Qdrant to OpenAI Agents SDK

Attach KosmoKrator integration tools to OpenAI Agents SDK workflows through a local MCP gateway.

Start the KosmoKrator MCP gateway locally and point the OpenAI Agents SDK MCP tool at that process or wrapper. The gateway is local, scoped to this integration, and starts with --write=deny so OpenAI Agents can inspect read-capable tools without receiving write access by default.

Qdrant MCP Config for OpenAI Agents SDK

Use headless JSON commands for CI-style execution and MCP for agent tool discovery.

{
  "mcpServers": {
    "kosmokrator-qdrant": {
      "type": "stdio",
      "command": "kosmo",
      "args": [
        "mcp:serve",
        "--integration=qdrant",
        "--write=deny"
      ]
    }
  }
}

Run the Gateway Manually

kosmokrator mcp:serve --integration=qdrant --write=deny

Why Use KosmoKrator Here

Scoped tools

Expose only Qdrant instead of a broad multi-service tool list.

Local credentials

Reuse credentials already configured for the KosmoKrator CLI and Lua runtime.

Write policy

Start read-only, then opt into ask or allow for trusted workspaces.

Qdrant Tools Visible to OpenAI Agents

OpenAI Agents sees stable MCP tool names generated from the Qdrant integration catalog.

MCP toolSource functionTypeDescription
integration__qdrant__qdrant_list_collections qdrant.qdrant_list_collections Read List all vector collections in the Qdrant cluster. Returns collection names and basic metadata.
integration__qdrant__qdrant_get_collection qdrant.qdrant_get_collection Read Get detailed information about a specific Qdrant collection, including vector configuration, index status, and point count.
integration__qdrant__qdrant_create_collection qdrant.qdrant_create_collection Write Create a new vector collection in Qdrant. You must specify the vector configuration (size, distance metric). Optionally provide HNSW, quantization, and optimization settings.
integration__qdrant__qdrant_search qdrant.qdrant_search Read Search for the closest vectors in a Qdrant collection. Supports vector similarity search with optional filtering, payload selection, and scoring.
integration__qdrant__qdrant_upsert_points qdrant.qdrant_upsert_points 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.
integration__qdrant__qdrant_get_current_user qdrant.qdrant_get_current_user Read Get information about the Qdrant cluster, including cluster status, node information, and the authenticated user context.

Related Qdrant Pages

Qdrant CLIUse direct JSON commands instead of MCP discovery. Qdrant MCPFull gateway reference and MCP tool names. KosmoKrator for OpenAI AgentsClient-level gateway setup.