Initial commit: RAG MCP Server with relationship graph

Features:
- Vector search with Pinecone + Vertex AI embeddings
- Document relationships (link, unlink, related, graph)
- Auto-link with LLM analysis
- Intelligent merge with Gemini

Modular structure:
- clients/: Pinecone, Vertex AI
- tools/: core, relations, stats
- utils/: validation, logging

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

server.py

@@ -0,0 +1,43 @@
+"""
+RAG System MCP Server Entry Point
+
+Refactored modular structure with:
+- config.py: Environment variables and constants
+- clients/: Pinecone and Vertex AI clients
+- tools/: MCP tool implementations
+- utils/: Validation and logging
+"""
+from fastmcp import FastMCP
+from config import FASTMCP_HOST, FASTMCP_PORT
+from utils import setup_logging
+from tools import (
+    rag_save,
+    rag_retrieve,
+    rag_update,
+    rag_delete,
+    rag_link,
+    rag_unlink,
+    rag_related,
+    rag_graph,
+    rag_stats
+)
+
+# Setup logging
+setup_logging()
+
+# Initialize FastMCP server
+mcp = FastMCP("RAG")
+
+# Register tools
+mcp.tool()(rag_save)
+mcp.tool()(rag_retrieve)
+mcp.tool()(rag_update)
+mcp.tool()(rag_delete)
+mcp.tool()(rag_link)
+mcp.tool()(rag_unlink)
+mcp.tool()(rag_related)
+mcp.tool()(rag_graph)
+mcp.tool()(rag_stats)
+
+if __name__ == "__main__":
+    mcp.run(transport="http", host=FASTMCP_HOST, port=FASTMCP_PORT)