connect

Put the records inside your AI

Ask Claude or ChatGPT what a building on Lake Street last sold for and it will guess. Paste this one address into its settings and it stops guessing — it reads 23 files of Minneapolis–St. Paul public records instead, 1,573,930 rows of them. Takes about thirty seconds. It is free, it needs no account and no key, and it can only read.

Thirty seconds, in whichever one you use

# or, in Claude Code:
claude mcp add --transport http \
  bricks https://brickandmortar.dev/mcp

{ "url": "https://brickandmortar.dev/mcp" }

What it can answer once it is in

Two of the 11 tools read the records themselves — every dataset this site publishes, the same files on the download page, joined and queryable without a download. Sales, parcels, assessed values, licences, permits, inspections, emergency calls, contamination, flood, wages.

The other 9 are frameworks rather than data, and they work in any American metro, not only this one:

• Data Source Atlas — Given a real question about a local market or a specific property, returns a source-first RESEARCH PLAN: which public record actually settles the question, how to reach it directly (county parcel GIS, Census CBP/ACS/permits, BLS series, state registries, licences, inspections), what the answer will be worth, and what the public record cannot answer at all.
• Business Teardown — Full structured teardown of ONE named small business: digital presence, review signal, competitive position, pricing posture, visibility gaps, and prioritized, evidence-cited recommendations.
• Competitor Landscape — Maps the local competitive set for a category + metro: true competitors vs.
• Review Intelligence — Mines public reviews for signal: a complaint taxonomy, theme extraction, sentiment trajectory over time, the differentiators customers actually cite, and red flags for a buyer.
• Local Visibility Audit — Audits a business's local search presence: map-pack factors, listing consistency, category selection, site fundamentals — what to check, and in what order — returned as a scored checklist.
• Pricing Benchmark — Builds a defensible local pricing comparison within a category: how to normalize across differing service bundles, and what to do when competitors don't publish prices at all.
• Broker Diligence Prep — Pre-diligence framework for a business broker or buyer evaluating a target: SDE framing (why the discretionary-earnings figure, not net income or raw EBITDA, is the relevant number, and what typically gets added back), a category multiple range the model must research fresh and date-stamp (never a hardcoded table), a public-signal red-flag checklist run before any financials are shared, and a prioritized seller-question list built from the specific gaps the research actually surfaces.
• Market Opportunity Scan — Gap analysis for a category x metro: detects underserved demand, oversaturation, and genuine whitespace using only public signals — for someone deciding whether/where to open, expand, or invest.
• Compose Report — Assembles the outputs of any prior Small Business Intelligence tool calls into one polished, client-ready report: section order, executive-summary rules, evidence-citation standards, and tone guidance matched to the audience.