mcp-rag-assistant
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | The LLM model to use, e.g., llama3:latest or mistral:latest | llama3:latest |
| CHUNK_SIZE | No | Tokens per chunk. Smaller = more precise retrieval | 256 |
| EMBED_MODEL | No | The embedding model to use, e.g., qwen3-embedding:0.6b or nomic-embed-text:latest | qwen3-embedding:0.6b |
| CHUNK_OVERLAP | No | Overlap between chunks. Helps preserve context at boundaries | 25 |
| RESPONSE_MODE | No | Response mode: compact, tree_summarize, or refine | compact |
| SIMILARITY_TOP_K | No | Number of chunks retrieved per query | 5 |
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 | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Hassan-Butt4356/mcp-rag-assistant'
If you have feedback or need assistance with the MCP directory API, please join our Discord server