Skip to main content
Glama
aniliou-85

RAG MCP Gateway

by aniliou-85

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GEMINI_API_KEYNoAPI Key for Google Generative AI. Required for enrichment.
RAG_MCP_DB_PATHNoPath to the Orama persistence folder.BASE_DIR/data/orama_db
RAG_MCP_BASE_DIRNoBase directory for all relative paths.process.cwd()
RAG_MCP_LOG_PATHNoPath to the debug log file.BASE_DIR/rag-mcp.log
RAG_MCP_ENABLE_LLMNoEnable LLM enrichment (summaries and questions) during indexing.false
RAG_MCP_CONFIG_PATHNoPath to the downstream servers config file.BASE_DIR/config.json
RAG_MCP_ENABLE_DENSENoEnable semantic vector search (Dense retrieval).true
RAG_MCP_ENABLE_SPARSENoEnable full-text keyword search (Sparse retrieval).true
RAG_MCP_REBUILD_INDEXNoSet to 'true' to force a full re-index on every startup.false
RAG_MCP_EMBEDDING_MODELNoTransformers.js model for generating vector embeddings. Required if Dense enabled.
RAG_MCP_ENABLE_RERANKERNoEnable the cross-encoder reranking stage.true
RAG_MCP_LOGGING_ENABLEDNoSet to 'true' to enable debug logging to the log file.false
RAG_MCP_RERANKING_MODELNoTransformers.js model for second-stage reranking. Required if Reranker enabled.
RAG_MCP_GENERATIVE_MODELNoGoogle Gemini model for tool enrichment. Required if LLM enabled.
RAG_MCP_SEARCH_THRESHOLDNoMinimum relevance score (0.0 to 1.0) for search results.0.85

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/aniliou-85/rag-mcp'

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