Superlinked Engineer Filip Makraduli Demonstrates Local AI Workflow: Processing Sensitive Documents with MCP and Small Models
In a video published on October 11, 2026, Filip Makraduli of Superlinked demonstrated a workflow transforming an Obsidian vault into a local AI engineering environment. The solution uses MCP integration and Superlinked's inference engine to perform document preprocessing tasks like OCR, summarization, and redaction via small open models on team-controlled infrastructure, reducing the cost and risk of sending raw sensitive data to large models. The video details the configuration of hosts, MCP servers, and GPU worker pools, and explores whether privacy boundaries truly hold.
For AI engineers needing to process sensitive documents in local environments, balancing privacy protection with reduced reliance on expensive cloud models is a practical challenge. In a video published on October 11, 2026, Filip Makraduli of Superlinked demonstrated a workflow architecture based on an Obsidian knowledge base, Model Context Protocol (MCP) integration, and Superlinked's inference engine.
The core idea of this workflow is to offload document preprocessing tasks from the coding agent. Makraduli showed how to use small open models on team-owned GPU infrastructure to perform operations such as OCR, summarization, question answering, and redaction. For instance, a scanned Non-Disclosure Agreement (NDA) is first converted into a redacted Markdown document before being used by the coding agent. This approach avoids sending every raw image or text page directly to costly and potentially non-compliant large models, instead returning a smaller, safer artifact for subsequent agent processing.
The video further dissects the infrastructure components supporting this flow, including hosts, MCP servers, and GPU worker pools. Makraduli explained how these choices connect with embeddings, reranking, task-specific LoRA fine-tuning, and model routing to optimize resource utilization. He also conducted a live exercise starting from an inbox of synthetic files, asking the agent to process a document through configured tools.