Second Brain - AI-Accessible Personal Knowledge Base over MCP
A self-hosted second brain: an Obsidian vault made readable AND writable by any AI via MCP - local RAG (Ollama + Qdrant), DeepSeek generation, human-validated AI writes.
My role
AI Architect & Software Engineer
Period
September 2026 - ongoing
Production n8n Workflows
Ingestion, KB Query, Add Note, Housekeeping, MCP Server
Extra API Cost
100% local embeddings (Ollama) + existing opencode key
MCP Tools
second_brain_ask (read) + second_brain_add (write) behind a single URL
Duplicate Gate
Redundant writes refused, warning from 55% similarity
Personal AI engineering project: a second brain - an Obsidian knowledge base versioned on a private GitHub repo, indexed by n8n into Qdrant (100% local Ollama bge-m3 embeddings) and generated with DeepSeek V4 Flash Vision. Exposed to any AI through a dedicated MCP server: reading (RAG with sources) and writing (auto-classified notes, deduplicated, held in quarantine until human validation).
01. Re-Explaining Context in Every Conversation
Every AI conversation started from zero: I had to re-explain who I am, my projects, my skills, my CV - scattered, outdated context, and no AI has a durable memory I control. I wanted a knowledge base any AI could query AND enrich, without depending on a single tool.
"An AI doesn't need to memorize everything: it should be able to read my base when needed - and only write to it with my approval."
02. Dedicated MCP Server, Local RAG & Human Validation
The architecture relies on a dedicated MCP server (MCP Server Trigger + Custom Workflow Tool) exposing only two tools, never n8n's admin surface. Reading runs through a full RAG: local Ollama bge-m3 embeddings, Qdrant semantic index, DeepSeek V4 Flash Vision generation via the OpenCode Go gateway. Writing is gated: every note proposed by an AI is auto-classified (type, tags, folder), checked against duplicates, and quarantined (status: pending) until validation.
Scoped MCP (2 tools only)
second_brain_ask + second_brain_add - never n8n's admin tools.
Privacy by design
100% local embeddings (Ollama) on my VPS - no third party indexes my notes.
Quarantine & human validation
No AI write enters the base without approval (anti prompt-injection).
Deduplication + classification
Semantic similarity (refuse ≥ 75%), LLM classification (type, tags, folder), weekly report.
03. Impact & Results
A single MCP URL is enough: ChatGPT, Claude, Cursor or opencode can read my base (sourced answers) and enrich it (classified, quarantined notes). Everything runs in production with zero extra API cost, and a quality pipeline (dedup on write, weekly housekeeping) keeps the base clean and well-organized.
A similar project?
Let's discuss your needs. I will get back to you within 24 hours with a concrete analysis.