Scrape every UK council planning portal with Claude and monitor it over MCP

A developer built a planning-applications scraper for every UK local planning authority with Claude, then added an MCP view of scraper health.

Difficulty
AdvancedOur rating
Time to build
Not reportedOur estimate
Monthly cost
Not reported
Revenue
Not reportedWe only show revenue the source states
Engagement
0 replies to HN commentComment in “Ask HN: Who is using MCP in production?” (198 points, 201 comments) · fetched Oct 15, 2026

What they did

mootothemax built a scraper for every UK council and planning authority with Claude’s help, plus a debugging front end. On a whim he asked Claude to add an MCP interface reporting last run status, what works, and coverage gaps.

How it went

He uses it to find unknown unknowns quickly while maintaining the scraper.

Worth knowing

For scrapers, the hard part is everything around the mechanics: coverage, failures and patterns.

Builder recipe

Our own starting point, written from the source. Adapt it to your setup.

Stack

  • Claude / Claude Code
  • A scraping framework
  • MCP server exposing run status

Steps

  1. Connect listings, calendar and messaging.
  2. Let the agent handle routine questions and scheduling.
  3. Keep a human on negotiations and compliance.
  4. Log every interaction.

Starter prompt

Using the scraper-status tool, list councils whose last run failed or returned zero results, group them by error, and propose a fix for the biggest group.

Tags

Read the original

Related use cases

The Daily 5.

Five real AI agent use cases each morning, each with a recipe and a source. Plus a Sunday roundup. Free.