Case study · 2025

Content intelligence engine

GSC and Ahrefs data, surfaced through MCP, driving content prioritization and decisioning instead of guesswork.

Role: Architect and engineer

Problem

Editorial decisions were made on intuition. There was no live, consolidated read on search demand, competitor movement, or content decay, so effort went to pages that did not need it and missed the ones that did.

Constraints

The signal had to come from authoritative sources (Search Console plus Ahrefs), not a model’s guess. It had to be consumable by non-engineers, and it had to be cheap enough to run continuously.

System

A first production version (v1) aggregates Search Console and Ahrefs data and exposes it to the workflow through the Model Context Protocol, so prioritization is driven by real performance data rather than opinion. A re-architected v2 with a new stack and broader feature set is in progress.

GSCAhrefsMCP layerprioritization
GSC + Ahrefs -> MCP -> prioritization

Outcome

Version 1 shipped to production and moved editorial prioritization from opinion to data-backed decisions, putting authoritative performance data directly into the content workflow: competitive research and content briefs that took days now take under an hour. Version 2 is being rebuilt on a new stack with broader functionality.

Stack

Next.js for the interface, the Model Context Protocol for tool access, and the Search Console and Ahrefs APIs as the data sources.

Outcome

v1
shipped to production, v2 rebuild in progress
<1 hour
research and briefs that took days before
data-led
prioritization moved from opinion to evidence

Stack

Next.jsMCPGoogle Search ConsoleAhrefs API

Hiring for SEO leadership, or have a project in mind? Let's talk.