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.

pyproject.toml

@@ -0,0 +1,21 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.backends.legacy:build"
+
+[project]
+name = "oracle-26ai-vector"
+version = "0.1.0"
+description = "MCP server for Oracle 23ai vector store with OCI GenAI Cohere Embed v4"
+requires-python = ">=3.11"
+dependencies = [
+    "mcp[cli]>=1.0.0",
+    "oracledb>=2.0.0",
+    "oci>=2.100.0",
+    "python-dotenv>=1.0.0",
+]
+
+[project.scripts]
+oracle-26ai-vector = "src.server:main"
+
+[tool.setuptools.packages.find]
+where = ["."]