Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
NEO4J_URINoNeo4j URI (default: bolt://localhost:7687).bolt://localhost:7687
MILVUS_URINoMilvus URI (default: rag_storage/milvus_lite.db).rag_storage/milvus_lite.db
WORKING_DIRNoDirectory for RAG-Anything working files (no default, must be set).
MINERU_TABLENoEnable table detection in MinerU (default: false).false
MILVUS_DB_NAMENoMilvus database name (default: empty).
MINERU_API_KEYNoAPI key for MinerU API (required when MINERU_EXECUTION_MODE=api).
MINERU_FORMULANoEnable formula detection in MinerU (default: false).false
NEO4J_DATABASENoNeo4j database name (default: neo4j).neo4j
NEO4J_PASSWORDNoNeo4j password (required when using Neo4JStorage).
NEO4J_USERNAMENoNeo4j username (default: neo4j).neo4j
PARSER_BACKENDNoMinerU parser backend (default: pipeline).pipeline
NEO4J_WORKSPACENoNeo4j workspace name (default: raganything).raganything
MILVUS_INDEX_TYPENoMilvus index type (default: AUTOINDEX).AUTOINDEX
MILVUS_METRIC_TYPENoMilvus metric type (default: COSINE).COSINE
EMBEDDING_BATCH_NUMNoNumber of items to embed in one batch (default: 4).4
JOB_TIMEOUT_SECONDSNoOverall timeout for a background job in seconds (default: 3600).3600
MINERU_API_BASE_URLNoBase URL for MinerU API (default: https://mineru.net).https://mineru.net
MINERU_EXECUTION_MODENoMinerU execution mode: local or api (default: local).local
MODEL_DOWNLOAD_POLICYNoModel download policy: auto, never, or require-ready (default: auto).auto
LIGHTRAG_GRAPH_STORAGENoGraph storage backend for LightRAG (default: NetworkXStorage).NetworkXStorage
PARSER_TIMEOUT_SECONDSNoTimeout in seconds for parsing a file (default: 120).120
LIGHTRAG_VECTOR_STORAGENoVector storage backend for LightRAG (default: NanoVectorDBStorage).NanoVectorDBStorage
EMBEDDING_FUNC_MAX_ASYNCNoMaximum number of concurrent embedding requests (default: 2).2
EMBEDDING_TIMEOUT_SECONDSNoTimeout for embedding requests in seconds (default: 180).180
MINERU_API_TIMEOUT_SECONDSNoTimeout for MinerU API requests in seconds (default: 1800).1800
MULTIMODAL_TIMEOUT_SECONDSNoTimeout for multimodal postprocessing in seconds (default: empty, meaning no limit).
TEXT_INGEST_TIMEOUT_SECONDSNoTimeout in seconds for text ingestion phase (default: 1800).1800
MODEL_DOWNLOAD_TIMEOUT_SECONDSNoTimeout in seconds for model downloads (default: 1800).1800
MINERU_API_POLL_INTERVAL_SECONDSNoPolling interval in seconds for MinerU API (default: 5).5

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/yyisahandsomeboy/rag_anything_mcp_sever'

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