update the readme files

README.md

@@ -37,7 +37,7 @@ This platform showcases how MCP can power intelligent, governed, multi-tenant AI
   - Per-tenant query volume and active users
   - Red-flag violations with timestamps and confidence scores
   - LLM token logs and latency metrics
-- 🌐 **Live Web Search** – DuckDuckGo-based MCP server with English-biased results
+- 🌐 **Live Web Search** – Google Programmable Search (Custom Search API) with tenant-aware MCP tooling
 - 🏢 **Multi-Tenant Isolation** – Complete tenant isolation with centralized tenant ID management; backend enforces strict isolation for chat, ingestion, and admin ops
 - 🔄 **Intelligent Multi-Tool Orchestration** – MCP agent orchestrator autonomously selects optimal tool chains (RAG + Web + LLM, etc.) based on query intent and context
 - ⚡ **Robust Error Handling** – Structured error responses, retry mechanisms, and graceful fallbacks (e.g., if RAG fails → fallback to LLM-only)
@@ -68,6 +68,10 @@ This platform showcases how MCP can power intelligent, governed, multi-tenant AI
    
    **Quick Start**: Run `start.bat` (Windows) to launch all services automatically.
 2. **Python 3.10+** with the dependencies in `requirements.txt`
+3. **Google Custom Search credentials** for live web search:
+   - Enable the *Custom Search API* in the [Google Cloud Console](https://console.cloud.google.com/) and create an API key → set it as `GOOGLE_SEARCH_API_KEY` in `.env`
+   - Create a Programmable Search Engine that searches the entire web and copy its *Search engine ID* → set it as `GOOGLE_SEARCH_CX_ID` in `.env`
+   - Restart the backend after updating `.env` so the new variables are picked up
 
 ### Installation