Universal RAG MCP Server
by rtostudioco
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RAG_TOP_K | No | Number of retrieved chunks | 5 |
| RAG_ASR_MODEL | No | Whisper ASR model: tiny | base | small | medium | large-v3 | base |
| RAG_LLM_MODEL | No | Model name for the OpenAI-compatible LLM endpoint | gpt-4o-mini |
| RAG_CHUNK_SIZE | No | Chunk size for splitting documents | 900 |
| RAG_CHROMA_PATH | No | Persistence path for the index | ./data/chroma |
| RAG_LLM_API_KEY | No | API key for the OpenAI-compatible LLM endpoint | |
| RAG_ASR_LANGUAGE | No | ASR language code (e.g. es, en) or auto | |
| RAG_LLM_BASE_URL | No | OpenAI-compatible endpoint; empty enables extractive mode | |
| RAG_CHUNK_OVERLAP | No | Chunk overlap for splitting documents | 150 |
| RAG_CONNECTOR_DIRS | No | Directories containing external connectors | |
| RAG_STORE_PROVIDER | No | Vector store provider: chroma | memory | chroma |
| RAG_EMBEDDING_MODEL | No | Local multilingual embedding model | paraphrase-multilingual-MiniLM-L12-v2 |
| RAG_EMBEDDING_PROVIDER | No | Embedding provider: auto | sentence-transformers | hash | auto |
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
ActivityMaintained
ResponsivenessNo issues