Skip to main content
Glama

AgenticRAG MCP Server

by aibozo
MIT License
  • Apple
  • Linux

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LOG_FILENoLog file path./logs/agenticrag.log
LOG_LEVELNoLogging levelINFO
OPENAI_API_KEYYesOpenAI API key required for embeddings and GPT-4
DAILY_BUDGET_USDNoCost control limit in USD100
MAX_FILE_SIZE_MBNoMaximum file size to index in MB2
ANTHROPIC_API_KEYNoOptional API key for Claude models
CHUNK_SIZE_TOKENSNoSize of code chunks in tokens1280
DEFAULT_LLM_MODELNoDefault LLM model to usegpt-4o
EMBEDDING_BATCH_SIZENoBatch size for embedding processing
DEFAULT_EMBEDDING_MODELNoDefault embedding model to usetext-embedding-3-large
CHROMA_PERSIST_DIRECTORYNoVector database storage directory./chroma_db

Schema

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

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/aibozo/agenticRAG-MCP'

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