rag-mcp
by mmelmesary
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| QDRANT_URL | No | URL of the Qdrant server (e.g. http://localhost:6333). | |
| EMBEDDINGS_MODEL | No | Embedding model name (e.g. text-embedding-3-small). Ingest and query must share provider and model. | |
| EMBEDDINGS_API_KEY | No | API key for the hosted embedding provider. | |
| RAG_INTERNAL_TOKEN | No | Token to gate the optional internal write API routes (/internal/knowledge/*). Not visible to the LLM. | |
| EMBEDDINGS_BASE_URL | No | Base URL for the OpenAI-compatible embeddings endpoint (e.g. https://api.openai.com). | |
| EMBEDDINGS_PROVIDER | No | Embedding provider. Defaults to local Ollama; set to 'openai' to use an OpenAI-compatible /v1/embeddings endpoint. |
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