Skip to main content
Glama
marlian

qdrant-mcp-hybrid

by marlian

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DEBUGNoEnable debug loggingfalse
LLM_MODELNoLLM model name for summarizationqwen/qwen3-8b
BATCH_SIZENoBatch size for embedding10
CHUNK_SIZENoChunk size for document splitting500
QDRANT_URLNoQdrant server URLhttp://localhost:6333
CONCURRENCYNoNumber of concurrent operations5
CHUNK_OVERLAPNoOverlap between chunks10
EMBEDDING_DIMNoEmbedding dimensions1024
LM_STUDIO_URLNoLM Studio server URLhttp://127.0.0.1:1235
QDRANT_API_KEYNoAPI key for Qdrant Cloud (optional)
EMBEDDING_MODELNoEmbedding model name in LM Studiotext-embedding-finetuned-bge-m3
CLIENT_COLLECTIONSNoComma-separated list of client names

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/marlian/claude-qdrant-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server