@Dominick Prevete
Basic information
Transport
Streamable HTTP
Authentication
None
Category
Finance & Commerce
Author
Dominick Prevete
Submitted by
Dominick Prevete
HMDA investor-lender data, DSCR glossary, loan programs and indicative rates. Business-purpose only.
https://dominickprevete.com/api/mcpclaude mcp add dominick-prevete-dscr-lender-data --transport http https://dominickprevete.com/api/mcpTop investment-property lenders in one of the 26 covered states, from 2025 HMDA loan-level data: lender name, LEI, loan count, volume, average loan and purchase share, plus state totals and the retrieval date. Read-only; figures are the filing record, not a recommendation.
Every HMDA filer across the 26 covered states grouped by LEI and ranked by 2025 investor-property loan count, with the number of states each filer reported in, the universe totals and the top-25 concentration share. The same computation https://dominickprevete.com/investor-property-lenders renders. A 26-state aggregate, not a national one.
How the investor-lender data is built: the filter definition, the server-side versus local filtering split, the vintage and retrieval date, the covered states, and the stated limitations an agent should attach to any figure it reports.
Definitions from the DSCR and investor-loan glossary (26 terms). Pass a term to look it up (case-insensitive, partial matches accepted) or no argument to list every term. Definitions describe what a term is; none states a program parameter.
The National Loan Provider program set — dscr, dscr_cash_out, short_term_rental, fix_and_flip, ground_up, rental_portfolio, bridge, commercial — each with the parameters its page already publishes, its starting rate from the site's single rate source with the as-of stamp, and the page URL. Where a page states no figure, the tool states no figure.
Indicative starting rate by program, from the site's single rate source, stamped with its as-of month (currently October 2026). These are the published ranges, not pricing on any deal.
The entity answer: legal name, business model (a mortgage brokerage that arranges and places financing and is not a lender), business-purpose scope and the owner-occupied exclusion, address, phone, the states with published investor-lending data, and the canonical Person @id for the founder.
A read-only MCP server for real estate investors researching DSCR and investment-property financing. It returns investor-lender rankings built from public HMDA data, by state across 15 states and in aggregate, along with the methodology behind them. It also provides a glossary of DSCR and investor-loan terms, an overview of available loan programs, and indicative rate ranges stamped with their as-of date. Every response carries the brokerage's disclosure. Financing is arranged for business-purpose, non-owner-occupied investment properties only; nothing returned is an offer, approval or commitment to lend.
The Dominick Prevete: DSCR Lender Data remote MCP server is a hosted Model Context Protocol endpoint at https://dominickprevete.com/api/mcp, so AI assistants can connect to it without installing or running anything locally.
Add the endpoint https://dominickprevete.com/api/mcp to any MCP-compatible client such as Claude Code, Cursor, or VS Code. The setup snippets on this page configure each client in one step.
No. Dominick Prevete: DSCR Lender Data's MCP server does not require authentication — you can connect directly with the endpoint URL.
Dominick Prevete: DSCR Lender Data exposes a Streamable HTTP endpoint, the transport used by remote MCP servers and supported by all major MCP clients.
Discover, evaluate, and buy solutions for the cloud
App Store keyword research, rank tracking, competitor analysis and authorized performance data.
Research competitors' winning ads, clone them for your brand and launch paused campaigns on Meta, Google and TikTok from chat.
Pay-per-use data and tools for AI agents: crypto token safety and rug checks, web search with cited answers, page-to-Markdown, up-to-date library docs, package safety, company research and UK/EU open data. 160 tools, 20
The 9apes MCP server lets an AI assistant read the GitHub Actions data 9apes already collects for your organization: runs, jobs, steps, and their durations. Ask it why a build got slower, which jobs take the longest, or
Comments