Skip to main content
Glama
gorizond

RAG Docs MCP Server

by gorizond

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
QDRANT_URLNoQdrant endpoint URL.http://localhost:6333
VECTOR_SIZENoOverride default vector dimension (openai=1536, ollama=768).
OPENAI_API_KEYNoAPI key for OpenAI (required when EMBEDDINGS_PROVIDER is 'openai').
QDRANT_API_KEYNoAPI key for Qdrant Cloud (optional for local).
EMBEDDING_MODELNoOverride default embedding model (provider-dependent).
OLLAMA_BASE_URLNoBase URL for local Ollama server.http://localhost:11434
OPENAI_BASE_URLNoCustom OpenAI-compatible endpoint URL (e.g., LM Studio).
EMBEDDINGS_PROVIDERNoThe embeddings provider to use. Options: 'openai' or 'ollama'.ollama
PLAYWRIGHT_WS_ENDPOINTNoWebSocket endpoint for remote Playwright server (optional).

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/gorizond/mcp-server-ragdocs'

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