Updated April 2026

Install Modular RAG MCP Server

Pick your client, copy the command, done.

Local setup required. This server has to be cloned and prepared on your machine before you register it in Claude Code.

Run this once to clone and prepare the server before adding it to Claude Code.

Run in terminal

git clone https://github.com/IcedVodka/rag_mcp
cd Modular-RAG-MCP-Server

After the local setup is done, run this command to point Claude Code at the built server.

Run in terminal

claude mcp add -e "OPENAI_API_KEY=${OPENAI_API_KEY}" modular-rag-mcp -- python "<FULL_PATH_TO_RAG_MCP>/dist/index.js"

Replace <FULL_PATH_TO_RAG_MCP>/dist/index.js with the actual folder you prepared in step 1.

Required:OPENAI_API_KEY

Environment Variables

Set these before running Modular RAG MCP Server.

VariableDescriptionRequired

OPENAI_API_KEYAPI key for LLM and Embedding servicesYes

Once configured, Modular RAG MCP Server gives your AI agent access to:

query_knowledge_hubPerforms hybrid search across the knowledge base using dense and sparse retrieval.

query

list_collectionsLists all available document collections in the knowledge hub.

get_document_summaryRetrieves a summary for a specific document.

document_id

After setup, try these prompts with your AI agent:

→Search the knowledge hub for information regarding the latest project specifications.

→List all available document collections to see what data is currently indexed.

→Get a summary of the document with ID 123 to understand its core content.

→Perform a hybrid search for 'RAG evaluation metrics' and summarize the findings.

Save the docs, env vars, and workflow around Modular RAG MCP Server in Conare so Claude Code, Codex, and Cursor remember it next time.