RAG Chat Assistant MCP Server
by AP46593
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CHUNK_SIZE | No | Characters per chunk (~500 tokens) | 2000 |
| MAX_TOKENS | No | Max tokens for generated responses | 2048 |
| PII_USE_LLM | No | Enable LLM-based PII detection (slower, catches more) | false |
| TEMPERATURE | No | LLM temperature | 0.7 |
| VISION_MODEL | No | Cloud vision model (OCR fallback) | gemma4:31b-cloud |
| CHUNK_OVERLAP | No | Overlap between consecutive chunks | 200 |
| DEFAULT_MODEL | No | Chat model for answer generation | gpt-oss:120b-cloud |
| EMBEDDING_MODEL | No | Embedding model for vector search | nomic-embed-text |
| MCP_SERVER_PORT | No | Server port | 8000 |
| OLLAMA_BASE_URL | No | Ollama API endpoint | http://localhost:11434 |
| RETRIEVAL_TOP_K | No | Number of chunks to retrieve | 5 |
| SEMANTIC_WEIGHT | No | Semantic vs keyword balance (0.7 = 70% semantic) | 0.7 |
| ENABLE_RAGAS_EVAL | No | Auto-evaluate responses with RAGAS | false |
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 recent community issues