rag-hub-mcp
by openhoat
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP listen port. HTTP mode only | 8000 |
| DB_PATH | No | SQLite database path | ./rag.db (stdio) / /data/index/rag.db (http) |
| KB_ROOT | No | Root directory for knowledge base folders | ./kbs (stdio) / /data/kbs (http) |
| MCP_API_KEY | No | Bearer token for REST endpoints. Required in HTTP mode, ignored in stdio mode. | |
| RAG_TRANSPORT | No | stdio or http. --http flag wins | stdio |
| SCAN_INTERVAL | No | Scan interval in seconds (0 = disabled). HTTP mode only | 300 |
| EMBEDDINGS_MODEL | No | Embedding model name | bge-m3 |
| EMBEDDINGS_API_KEY | No | Bearer token for the embeddings API | |
| EMBEDDINGS_BASE_URL | No | OpenAI-compatible /v1/embeddings endpoint | http://localhost:11434/v1 |
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