Skip to main content
Glama
nguyenngocdue

RAG-Anything MCP Server

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LLM_MODELNoLanguage model to use for LLM tasks (default: gpt-4o-mini). Overridden by MODEL_PROFILE.gpt-4o-mini
LOG_LEVELNoLogging level (default: INFO).INFO
UPLOAD_DIRNoDirectory for uploaded files (default: ./uploads)../uploads
VISION_MODELNoVision model to use (default: gpt-4o). Overridden by MODEL_PROFILE.gpt-4o
EMBEDDING_DIMNoDimension of embeddings (default: 3072). Overridden by MODEL_PROFILE.3072
MAX_FILE_SIZENoMaximum file size in MB (default: 100).100
MODEL_PROFILENoName of a model profile defined in MODEL_PROFILES or MODEL_PROFILES_PATH. When set, overrides LLM_MODEL, VISION_MODEL, EMBEDDING_MODEL, and EMBEDDING_DIM.
MODEL_PROFILESNoJSON string containing profile definitions. Used if MODEL_PROFILE is set. Alternative to MODEL_PROFILES_PATH.
OPENAI_API_KEYYesYour OpenAI API key. Required.
EMBEDDING_MODELNoEmbedding model to use (default: text-embedding-3-large). Overridden by MODEL_PROFILE.text-embedding-3-large
OPENAI_BASE_URLNoOptional base URL for OpenAI API (e.g., https://api.openai.com/v1).
RAG_STORAGE_DIRNoDirectory for RAG storage (default: ./rag_storage)../rag_storage
MODEL_PROFILES_PATHNoPath to a JSON file with model profiles (default: ./model_profiles.json). Used if MODEL_PROFILE is set../model_profiles.json

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

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/nguyenngocdue/RAG-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server