Plug Homecastr into Claude, Cursor, ChatGPT, or any MCP-compatible agent. Your AI gets real probabilistic forecasts — not hallucinations.
Native MCP support in Claude Desktop and Claude.ai. Forecasts appear inline in conversation.
Drop into .cursor/mcp.json and your coding assistant can reason about home values.
Standard Model Context Protocol — works with any client that supports MCP 2024-11-05+.
# Install Homecastr MCP server npm install -g @homecastr/mcp-server # Or run directly with npx (no install) npx @homecastr/mcp-server
Edit ~/.claude/claude.json:
{
"mcpServers": {
"homecastr": {
"command": "node",
"args": ["/path/to/homecastr-mcp-server/dist/index.js"],
"env": {
"HOMECASTR_API_KEY": "YOUR_API_KEY"
}
}
}
}// .cursor/mcp.json
{
"mcpServers": {
"homecastr": {
"command": "node",
"args": ["/path/to/homecastr-mcp-server/dist/index.js"],
"env": { "HOMECASTR_API_KEY": "YOUR_API_KEY" }
}
}
}Free and instant — no sales call. Get your key →
User: What's the 5-year forecast for 123 Main St Houston TX?
Claude: Let me look that up for you.
[calls forecast_address("123 Main St Houston TX", 2030)]
Based on Homecastr's model, 123 Main St has a median forecast of $425,000
by 2030 (+12.5% appreciation). The confidence range is $385K–$480K.All tools are called automatically by the AI — you just describe what you want in plain English.
forecast_addressForecast home values by US street address. Geocodes automatically.
Parameters
| address* | string | US street address (e.g. "123 Main St Houston TX") |
| year | integer | Forecast year 2026–2030 (default: 2030) |
Returns
P10/P50/P90 forecast bands, appreciation %, multi-year fan chart, H3 cell ID
forecast_hexForecast by H3 cell ID for neighborhood-level analysis.
Parameters
| h3_id* | string | H3 cell ID at resolution 8 (e.g. 882a100c65fffff) |
| year | integer | Forecast year (default: 2026) |
Returns
Same as forecast_address
forecast_parcelForecast by tax parcel account ID. Supports Houston HCAD, NYC, Florida, Seattle.
Parameters
| acct* | string | County tax account / parcel ID |
| year | integer | Forecast year |
Returns
Parcel-level P10/P50/P90 forecast
get_market_overviewAggregate forecast for a market — county, state, or ZCTA.
Parameters
| geoid* | string | FIPS code or ZCTA (e.g. 48201 for Harris County) |
| year | integer | Forecast year |
Returns
Median forecast, appreciation, property count, geographic metadata
compare_marketsCompare forecasts across multiple locations side by side.
Parameters
| locations* | string[] | Array of addresses or GEOIDs to compare |
| year | integer | Forecast year |
Returns
Ranked comparison table with appreciation % and absolute forecast values
| Geography | Coverage | Scale |
|---|---|---|
| Parcel / Unit | Houston, NYC, Chicago, Seattle, Florida | 46M+ units |
| Census Block | NYC + Houston | 67K blocks |
| Census Tract | FL, Houston, nationwide (ACS) | 82K tracts |
| ZIP Code (ZCTA) | Nationwide | 20K ZCTAs |
| County | Nationwide | 3,230 counties |
| State | All 50 states + DC | 51 states |
Get a free API key and have your agent forecasting in under 2 minutes.
Look up a home and see where its value may be headed over the next five years.