Easy MCP RAG
by justinlime
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TOP_K | No | Results per search | 5 |
| DEVICE | No | Device: auto, cpu, cuda, mps | auto |
| VERBOSE | No | Enable verbose logging | false |
| DATA_DIR | Yes | Directory with document subdirectories (required) | |
| HTTP_HOST | No | HTTP server host | 0.0.0.0 |
| HTTP_PORT | No | HTTP server port | 8000 |
| LOG_LEVEL | No | Log level | INFO |
| TRANSPORT | No | Transport type: stdio, http | stdio |
| BATCH_SIZE | No | Embedding batch size | 32 |
| CHUNK_SIZE | No | Text chunk size (chars) | 512 |
| QDRANT_HOST | No | Qdrant server host | localhost |
| QDRANT_PORT | No | Qdrant server port | 6333 |
| CHUNK_OVERLAP | No | Chunk overlap (chars) | 50 |
| FORCE_REINDEX | No | Force reindex all docs | false |
| EMBEDDING_MODEL | No | Sentence transformer model | all-MiniLM-L6-v2 |
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