frc-mcp
OfficialThis read-only MCP server lets AI agents query historical 2025 FHA mortgage denial statistics, lender/state comparisons, official figures, and dated mortgage rules with receipts—never individual borrower predictions.
Get national FHA denial rates and volumes from the 2025 CFPB HMDA record.
Look up top-100 FHA lender denial stats by name, slug, or LEI, including peer median and mix-adjusted expected rate.
List lenders ranked by highest denial, lowest denial, or volume.
Get state-level FHA denial stats and small-loan vs large-loan gaps.
Analyze the “Door Effect”: how much denial variation is attributable to lender identity, plus strictest/most-lenient lender tables.
Check claim wording against use contracts, retrieve official figures with SHA-256 receipts, resolve FHA annual MIP, access dated rule tables, run public cohorts, locate denominators, inspect application outcomes, and verify citations/receipts.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@frc-mcp What are the national FHA denial rates from the 2025 HMDA data?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
frc-mcp — FinanceRateCalc MCP Server
Read-only statistics over the complete 2025 US HMDA mortgage record (1,187,606 FHA credit decisions, reverse mortgages excluded) plus dated, machine-readable US mortgage rule tables, served to AI agents over MCP. Every figure returns with its period, population and program scope, a use contract, and a receipt that can be verified later.
The red line: every figure is a historical aggregate. This server never accepts borrower details and never returns an individual approval prediction.
Remote endpoint (no install, no key)
https://frc-mcp.ziyetis.workers.devStreamable HTTP, stateless. MCP protocol revisions 2026-07-28, 2025-11-25, 2025-06-18,
2025-03-26. Server version 1.57.0 (tools, resources and prompts; get_official_figure returns figures from official publications restated as printed with the document's SHA-256 and revision status — Level-2 receipts; A2A agent card at /.well-known/agent-card.json; a citation envelope on every figure-bearing result; every claim document carries a keyless CFPB Data Browser reproduce query). Listed in the official MCP registry as
io.github.financeratecalc/frc-mcp.
Client configs (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Codex, Gemini CLI), an
instruction block for CLAUDE.md / AGENTS.md, and a first task to try:
https://financeratecalc.com/use-frc.html
Related MCP server: census-mcp
Tools (remote endpoint, 19)
Tool | What it answers |
| Checks a sentence you intend to write against the figure's use contract; fixed patterns, no model. Returns |
| 2025 national FHA denial rate with its universe. |
| One of the 100 largest FHA lenders: volume, denial rate, rank, applicant-mix caveat. |
| The 100 largest FHA lenders ranked by denial rate or volume. |
| State FHA denial rate and small-loan split. |
| Within one metro, the spread between the highest- and lowest-denying high-volume lenders. |
| Denial rate under $150K vs over $250K, by state. |
| Median and maximum share of each HMDA denial reason across the top-100 lenders. |
| Lender identity's share of explained variation in 2025 FHA denials. |
| Where FHA applications end: originated, approved-not-accepted, denied, withdrawn, closed-incomplete as shares of applications acted on, nationally or for one lender, with the reconciliation to the decisioned denial rate. |
| Which definition reproduces a quoted 2025 denial rate: program (FHA, VA) x loan purpose x scope x base, with counts. A match is not an attribution. |
| A figure from an official publication (HUD's FHA production report and FHA loan performance report, Ginnie Mae's issuance summary, SBA's 7(a) and 504 activity file) exactly as printed, with the document's SHA-256, table and row, period, exclusion note, revision status and a receipt; nothing computed. Params: source, period (YYYY-MM), figure. |
| Per-lender conditional surface with its robustness record. |
| Ready-made public cohorts; no upload needed. |
| One of five dated rule tables: FHA annual MIP (ML 2023-05), FHA forward loan limits 2026, FHFA conforming limits 2026, CFPB HOEPA/QM thresholds 2026, VA funding fee. |
| The MIP cell for a stated term, base loan amount and LTV; asks for a missing condition instead of guessing it. |
| Counterparty screen; free preview, full brief needs a licence bought by a human. The agent only relays the offer. |
Plain HTTP beside MCP: GET /server-card, GET /cite/<claim-id> (receipted sentence in text,
Markdown, HTML and BibTeX), GET /verify?r=<receipt> (is this figure still current; if not,
which correction superseded it).
Receipts
A figure travels with a receipt such as
⟦FRC:national-fha-denial-rate-2025:22.1%:ebf6b00b:m2610⟧: claim id, value, the first eight
hex characters of a hash of the claim object, and the channel and month it was issued through.
/verify answers current, stale (corrected since; the correction is returned),
hash-current-value-mismatch (the quoted value was edited) or unrecognized (this publisher
never issued it). Conformance runs on every deploy and is published:
https://financeratecalc.com/conformance.html
Local stdio package (npm)
The frc-mcp npm package is the original five read-only tools from a bundled data snapshot; it
does not carry the rule tables, the sentence gate or receipts. Prefer the remote endpoint.
{
"mcpServers": {
"financeratecalc": {
"command": "npx",
"args": ["-y", "frc-mcp"]
}
}
}Source
The remote server's source of record is worker/index.js in
https://github.com/financeratecalc/financeratecalc.github.io, deployed to Cloudflare Workers
on every change to that file. remote/worker.js in this repository is an early (five-tool)
copy kept for reference.
Data: CC BY 4.0, attribution to financeratecalc.com. Source of truth: public CFPB HMDA 2025 (loan_type 2; actions 1, 2, 3; denial = action 3). Method: https://financeratecalc.com/methodology.html · corrections log: https://financeratecalc.com/corrections.html · SSRN 7156938. No lender recommendations, no individual predictions, no lender pays for placement.
Available Tools
5 toolsget_door_effect_summaryAInspect
The Door Effect: variance decomposition across 859,090 FHA decisions — 38% of explainable variation in denial outcomes is attributable to lender identity rather than the applicant's file, plus mix-adjusted strictest/most-lenient lender tables. Historical observation computed from the public CFPB HMDA 2025 record (denominator: actions 1,2,3; loan_type 2). Not a prediction about any individual application, and not a recommendation for or against any lender. Attribution: FinanceRateCalc (financeratecalc.com), CC BY 4.0.
Inputs: no named parameters.
get_lender_denial_statsAInspect
FHA denial statistics for one lender by name, slug, or LEI: actual denial rate, peer-median comparison, mix-adjusted expected rate. Top-100 FHA lenders by volume are covered. Historical observation computed from the public CFPB HMDA 2025 record (denominator: actions 1,2,3; loan_type 2). Not a prediction about any individual application, and not a recommendation for or against any lender. Attribution: FinanceRateCalc (financeratecalc.com), CC BY 4.0.
Inputs: lender (required).
get_national_fha_statsAInspect
National FHA denial statistics from the 2025 federal record (denial rate on decisioned applications, volumes). Historical observation computed from the public CFPB HMDA 2025 record (denominator: actions 1,2,3; loan_type 2). Not a prediction about any individual application, and not a recommendation for or against any lender. Attribution: FinanceRateCalc (financeratecalc.com), CC BY 4.0.
Inputs: no named parameters.
get_state_denial_statsAInspect
FHA denial statistics for a US state (two-letter code), including the small-loan vs large-loan gap where published. Historical observation computed from the public CFPB HMDA 2025 record (denominator: actions 1,2,3; loan_type 2). Not a prediction about any individual application, and not a recommendation for or against any lender. Attribution: FinanceRateCalc (financeratecalc.com), CC BY 4.0.
Inputs: state (required).
list_lendersAInspect
List covered FHA lenders sorted by denial rate (highest/lowest) or volume. Useful to see how widely the same federal program is applied across doors (2025 span: 1.8% to 78.7%). Historical observation computed from the public CFPB HMDA 2025 record (denominator: actions 1,2,3; loan_type 2). Not a prediction about any individual application, and not a recommendation for or against any lender. Attribution: FinanceRateCalc (financeratecalc.com), CC BY 4.0.
Inputs: sort, limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool targets a distinct scope: national, lender-specific, state-level, lender listing, and door-effect analysis. There is minor overlap between list_lenders and the lender tables inside get_door_effect_summary, but the descriptions make the intended use clear.
Most tools follow a get_<scope>_stats pattern, which is predictable and readable. list_lenders and get_door_effect_summary deviate slightly from that pattern, but the naming remains consistent in style and verb usage.
Five tools is well-scoped for a specialized FHA denial statistics server. Each tool covers a meaningful slice of the domain without redundancy or bloat.
The tool surface covers national aggregates, state-level views, individual lender stats, lender rankings, and the cross-lender door effect analysis. For the stated purpose of exposing FHA denial statistics, there are no obvious missing operations or dead ends.
Maintenance
Related MCP Connectors
MCP server for US nursing facility search and ownership lookup (NursingHomeDatabase).
MCP server for the GovContractScout US government contracts API: search, NAICS, match scoring.
MCP server for nonprofit financials via ProPublica: IRS Form 990 data for 1.8M+ nonprofits.
Hosted MCP server exposing US hospital procedure cost data to AI assistants
Related MCP Servers
- AlicenseAqualityDmaintenanceMCP server for the loc8n Geographic Data API. Exposes U.S. demographics, housing, mortgage, migration, employment, and geographic data as tools.23MIT
- FlicenseNot gradedqualityCmaintenanceRemote MCP server exposing US Census (ACS 5-year) and FEMA flood data. Works as a connector in both Claude and ChatGPT.-
- AlicenseAqualityBmaintenanceMCP server for HUD housing data, enabling Fair Market Rent lookups, Section 8 income limits, and ZIP-to-county crosswalk mapping for affordable housing assessments.63 npmMIT
- AlicenseNot gradedqualityCmaintenanceChains FRED, BLS, ATTOM, and HUD APIs to provide housing intelligence data through a single MCP server.85 npm1MIT