feat: replace server-side RAG with MCP retrieval primitives

- Remove Phase 4 RAG pipeline in favor of retrieval-only architecture
- Add FastMCP server exposing search, get_chunk, list_libraries tools
- Mount MCP endpoints (streamable HTTP + SSE) via Starlette in ASGI config
- Update README to clarify Mnemosyne is a retrieval engine, not RAG
- Let calling LLMs drive synthesis and iterative retrieval themselves

mnemosyne/mcp_server/apps.py

@@ -0,0 +1,7 @@
+from django.apps import AppConfig
+
+
+class McpServerConfig(AppConfig):
+    default_auto_field = "django.db.models.BigAutoField"
+    name = "mcp_server"
+    verbose_name = "MCP Server"