NYC Property Data MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_salesA | Search for recent property sales in NYC. Filter by neighborhood, price range, building type, and more. Returns sales with price_per_unit and price_per_sqft. Results display on an interactive map. |
| get_propertyA | Get detailed property information including owner, units, zoning, coordinates, and rent stabilization analysis. Result displays on an interactive map. |
| get_sale_historyB | Get all recorded sales for a specific property. |
| search_propertiesC | Search property database for properties matching criteria. Results display on an interactive map. |
| get_tax_benefitsB | Get tax exemptions and abatements for a NYC property. Returns 421a, J-51, ICAP, STAR benefits. |
| get_deed_partiesA | Look up buyer (grantee) and seller (grantor) for a NYC property from ACRIS deed records. Use when the user specifically asks who bought or sold a property. |
| search_compsA | Find comparable sales for a subject property with similarity scoring. Results display on an interactive map. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| ui://property-mcp/property-map.html |
TDQS
Scored across 7 tools
Most tools have clear distinct purposes (property lookup, sales search, sale history, tax benefits, deed parties, comps). Minor overlap exists between search_sales and search_comps, as both return sales data, but the comps tool adds similarity scoring and context, reducing confusion.
All tool names follow a consistent verb_noun pattern with 'get_' for specific lookups and 'search_' for query operations. Naming is uniformly snake_case and predictable, making it easy to infer tool behavior.
With 7 tools, the server is well-scoped for a property data domain. Each tool serves a distinct function, and the count is within the ideal range for a focused server.
The toolset covers core property data needs: detailed property info, sales search/history, tax benefits, deed parties, and comps. Minor gaps such as property assessments or permits are absent, but the essential workflows for a property data server are well covered.