RAG MCP Server
by sglwsjxh
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RERANK_MODEL | No | Model name for reranking (e.g., nvidia/llama-nemotron-rerank-vl-1b-v2) | |
| DATABASE_PATH | No | Path to store vector database files | ./database |
| RERANK_API_KEY | Yes | API key for reranking service | |
| RERANK_BASEURL | No | Base URL for reranking API (e.g., NVIDIA) | |
| EMBEDDING_MODEL | No | Model name for embeddings (e.g., nvidia/llama-nemotron-embed-vl-1b-v2:free) | |
| EMBEDDING_API_KEY | Yes | API key for embedding service | |
| EMBEDDING_BASEURL | No | Base URL for embedding API (e.g., OpenRouter) |
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/sglwsjxh/rag-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server