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.
Description
MCP server: Oracle 23ai vector store + OCI GenAI Cohere Embed v4
Languages
Python
92.5%
PLSQL
7.5%