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 |
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 | |
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