Skip to main content
Glama
AP46593

RAG Chat Assistant MCP Server

by AP46593

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CHUNK_SIZENoCharacters per chunk (~500 tokens)2000
MAX_TOKENSNoMax tokens for generated responses2048
PII_USE_LLMNoEnable LLM-based PII detection (slower, catches more)false
TEMPERATURENoLLM temperature0.7
VISION_MODELNoCloud vision model (OCR fallback)gemma4:31b-cloud
CHUNK_OVERLAPNoOverlap between consecutive chunks200
DEFAULT_MODELNoChat model for answer generationgpt-oss:120b-cloud
EMBEDDING_MODELNoEmbedding model for vector searchnomic-embed-text
MCP_SERVER_PORTNoServer port8000
OLLAMA_BASE_URLNoOllama API endpointhttp://localhost:11434
RETRIEVAL_TOP_KNoNumber of chunks to retrieve5
SEMANTIC_WEIGHTNoSemantic vs keyword balance (0.7 = 70% semantic)0.7
ENABLE_RAGAS_EVALNoAuto-evaluate responses with RAGASfalse

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/AP46593/Enterprise_Knowledge_Assistant_v3.2'

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