qdrant-mcp-hybrid
by marlian
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEBUG | No | Enable debug logging | false |
| LLM_MODEL | No | LLM model name for summarization | qwen/qwen3-8b |
| BATCH_SIZE | No | Batch size for embedding | 10 |
| CHUNK_SIZE | No | Chunk size for document splitting | 500 |
| QDRANT_URL | No | Qdrant server URL | http://localhost:6333 |
| CONCURRENCY | No | Number of concurrent operations | 5 |
| CHUNK_OVERLAP | No | Overlap between chunks | 10 |
| EMBEDDING_DIM | No | Embedding dimensions | 1024 |
| LM_STUDIO_URL | No | LM Studio server URL | http://127.0.0.1:1235 |
| QDRANT_API_KEY | No | API key for Qdrant Cloud (optional) | |
| EMBEDDING_MODEL | No | Embedding model name in LM Studio | text-embedding-finetuned-bge-m3 |
| CLIENT_COLLECTIONS | No | Comma-separated list of client names |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessNo issues