feat: initial oracle-26ai-vector MCP server

MCP server exposing Oracle 23ai as a RAG vector store backed by
OCI GenAI Cohere Embed v4 (1536 dims). Three tools:
- insert_document: embed + store a text chunk
- update_document: re-embed + update an existing chunk
- search_similar: cosine similarity search (VECTOR_DISTANCE)

Uses python-oracledb thin mode with wallet (config_dir only).
Configured for Claude Code via ~/.claude/settings.json.

.env.example

@@ -0,0 +1,10 @@
+# Oracle DB connection
+ORACLE_USER=
+ORACLE_PASSWORD=
+ORACLE_DSN=          # TNS alias from tnsnames.ora, e.g. h8i4i0g8cxtd2lpf_high
+ORACLE_WALLET=       # Path to wallet directory, e.g. /Users/you/devkit/db_conn/Wallet_XXX
+
+# OCI GenAI (auth via ~/.oci/config)
+OCI_COMPARTMENT_ID=
+OCI_GENAI_ENDPOINT=  # e.g. https://inference.generativeai.us-chicago-1.oci.oraclecloud.com
+OCI_EMBED_MODEL_ID=cohere.embed-v4.0