Nyc Property Intel MCP Server

MCP server that gives Claude AI access to 20+ NYC public record datasets for real estate due diligence. Ask Claude about any NYC property in plain

Remote serverstreamable-httpPython

What is the Nyc Property Intel MCP server?

Nyc Property Intel MCP server is a hosted integration for AI assistants that speak the Model Context Protocol. MCP server that gives Claude AI access to 20+ NYC public record datasets for real estate due diligence. Ask Claude about any NYC property in plain English — violations, liens, sales history, ownership, permits, rent stabilization, zoning.

What the assistant can call

Once Nyc Property Intel is connected, these are the calls the assistant has available:

  • lookup_property — Resolve any NYC address or BBL to a full property profile: owner, building class, zoning, FAR, assessed value, lot dimensions. **Always call this
  • get_property_issues — HPD housing violations (Class A/B/C), DOB building code violations, and ECB/OATH monetary penalties. Filter by severity, status, and date
  • get_property_history — DOF sales records and ACRIS deed transfers. Price trajectory, buyer/seller names, document types going back to 2003
  • get_hpd_complaints — Tenant-reported HPD complaints — leading indicators of building distress before formal violations are issued
  • get_hpd_litigations — HPD housing court cases, open judgements, and harassment findings against building owners
  • get_hpd_registration — Legal owner, managing agent, and head officer registration records
  • get_building_permits — DOB job filings: new buildings, alterations, demolitions, sign permits. Status, cost estimate, applicant name
  • get_liens_and_encumbrances — DOF tax lien sale list entries and ACRIS mortgage records. Outstanding liens, lender names, amounts, satisfactions
  • get_tax_info — Tax assessments, market value estimates, taxable value, and active exemptions (421a, J-51, STAR)
  • get_rent_stabilization — Rent-stabilized unit counts by year (2007–2017). Trend analysis for deregulation signal
  • search_comps — Comparable sales by zip code. Filter by building class, price, date. Includes quarterly market stats
  • search_neighborhood_stats — Area-level aggregates: property stock, median sale prices, violation rates, rent stabilization share

Configuration and credentials

You will need 4 environment variables: DATABASE_URL, YOUR_TOKEN, NYC_GEOCLIENT_SUBSCRIPTION_KEY, SOCRATA_APP_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Python 3.12+ - uv package manager - PostgreSQL 16+ - nycdb CLI (pip install nycdb)

Setting it up

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Choosing this one

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Nyc Property Intel's toolset — lookup_property, get_property_issues, get_property_history and 11 more — is a fair guide to whether it matches your workflow. It is maintained by ccedacero; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Nyc Property Intel.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the nyc property intel mcp server does with a few real requests.

Available tools

ToolWhat it does
lookup_propertyResolve any NYC address or BBL to a full property profile: owner, building class, zoning, FAR, assessed value, lot dimensions. **Always call this first.**
get_property_issuesHPD housing violations (Class A/B/C), DOB building code violations, and ECB/OATH monetary penalties. Filter by severity, status, and date.
get_property_historyDOF sales records and ACRIS deed transfers. Price trajectory, buyer/seller names, document types going back to 2003.
get_hpd_complaintsTenant-reported HPD complaints — leading indicators of building distress before formal violations are issued.
get_hpd_litigationsHPD housing court cases, open judgements, and harassment findings against building owners.
get_hpd_registrationLegal owner, managing agent, and head officer registration records.
get_building_permitsDOB job filings: new buildings, alterations, demolitions, sign permits. Status, cost estimate, applicant name.
get_liens_and_encumbrancesDOF tax lien sale list entries and ACRIS mortgage records. Outstanding liens, lender names, amounts, satisfactions.
get_tax_infoTax assessments, market value estimates, taxable value, and active exemptions (421a, J-51, STAR).
get_rent_stabilizationRent-stabilized unit counts by year (2007–2017). Trend analysis for deregulation signal.
search_compsComparable sales by zip code. Filter by building class, price, date. Includes quarterly market stats.
search_neighborhood_statsArea-level aggregates: property stock, median sale prices, violation rates, rent stabilization share.
get_fdny_fire_incidentsFDNY fire and emergency incident history. Fire type, alarm level, spread, casualties, duration. 2013–present, loaded from NYC Open Data.
get_311_complaints311 service requests at or near a property. Noise, rodents, heat, illegal dumping, and 200+ types. 2010–present, loaded from NYC Open Data.

How to install the Nyc Property Intel MCP server

### 4. Add to Claude Desktop

```json
{
  "mcpServers": {
    "nyc-property-intel": {
      "command": "uv",
      "args": ["run", "nyc-property-intel"],
      "cwd": "/absolute/path/to/nyc-property-intel",
      "env": {
        "DATABASE_URL": "postgresql://nycdb:nycdb@localhost:5432/nycdb"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Python 3.12+ - uv package manager - PostgreSQL 16+ - nycdb CLI (pip install nycdb)
VariableDescriptionRequired
DATABASE_URLEndpoint or connection string the server talks to.Yes
YOUR_TOKENCredential the server authenticates with.Yes
NYC_GEOCLIENT_SUBSCRIPTION_KEYCredential the server authenticates with.Yes
SOCRATA_APP_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Nyc Property Intel to lookup property.
  • Use Nyc Property Intel to get property issues.
  • Use Nyc Property Intel to get property history.

Frequently asked questions

It connects Nyc Property Intel to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (lookup_property, get_property_issues, get_property_history, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Nyc Property Intel directly.