agentic-rag-mcp/
├── main.py                    # FastAPI MCP server
├── rag_agent.py              # Agent query logic and RAG orchestration
├── mcp_config.yaml           # Configuration file
├── requirements.txt          # Python dependencies
├── vector_store/             # Persisted ChromaDB vector store
├── data/
│   └── sample_docs/          # Sample documents for ingestion
└── tools/
    └── chromadb_tool.py      # Vector search tool implementation

cd agentic-rag-mcp
python -m venv .venv

# On Windows
.venv\Scripts\activate

# On macOS/Linux
source .venv/bin/activate

pip install -U pip
pip install -r requirements.txt

# On the system terminal (not in virtual environment)
ollama serve

ollama pull mistral    # Recommended for RAG
# or
ollama pull llama3

curl http://localhost:11434/api/tags

python rag_agent.py

You: What is MCP?
Agent: The Model Context Protocol (MCP) enables modular tool use for AI agents by providing a standardized way to connect language models to external services...

[Used 2 retrieved documents as context]

python main.py

GET /health

POST /query
Content-Type: application/json

{
  "query": "What is artificial intelligence?",
  "use_context": true,
  "n_results": 3
}

POST /search
Content-Type: application/json

{
  "query": "MCP protocol",
  "n_results": 5
}

POST /documents
Content-Type: application/json

{
  "documents": [
    "Document text 1",
    "Document text 2"
  ],
  "ids": ["doc1", "doc2"],
  "metadata": [
    {"source": "file1.txt"},
    {"source": "file2.txt"}
  ]
}

GET /stats

from rag_agent import RAGAgent

# Initialize agent
agent = RAGAgent(
    ollama_url="http://localhost:11434",
    model="mistral"
)

# Get a response
result = agent.get_response("What is RAG?")
print(result["response"])
print(f"Retrieved {len(result['retrieved_documents'])} documents")

from tools.chromadb_tool import ChromaTool

tool = ChromaTool()
documents = [
    "Your document text 1",
    "Your document text 2"
]
tool.add_documents(documents, ids=["id1", "id2"])

curl -X POST http://localhost:8000/documents \
  -H "Content-Type: application/json" \
  -d '{
    "documents": ["Document 1", "Document 2"],
    "ids": ["doc1", "doc2"]
  }'

import streamlit as st
import requests

st.set_page_config(page_title="RAG Agent", layout="wide")
st.title("MCP-Powered Agentic RAG")

query = st.text_input("Ask a question:")

if query:
    response = requests.post(
        "http://localhost:8000/query",
        json={"query": query}
    )
    result = response.json()
    
    st.subheader("Response")
    st.write(result["response"])
    
    st.subheader("Retrieved Context")
    for i, doc in enumerate(result["retrieved_documents"], 1):
        st.write(f"**Doc {i}**: {doc[:200]}...")

streamlit run streamlit_app.py