io.github.Zwondra由 GitHub 帳號 Zwondra 發布v1.1.0更新於 Oct 24, 2026
Live CRE analysis: Federal Reserve rates, Census 1/3/5-mile demographics, DCF models, IC memos.
託管式商用不動產分析伺服器，讓助理取得美國聯準會即時利率與人口普查資料，並進行 DCF 建模、租約與租金表解析及投資委員會備忘錄產生。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/io.github.Zwondra%2Fcre-intelligence-mcp/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"cre-intelligence": {
"type": "http",
"url": "https://cre-intelligence-mcp.onrender.com/mcp"
}
}
}Live market data for commercial real estate analysis — inside Claude.
Connect this MCP to Claude Desktop and instantly access Federal Reserve interest rates, Census Bureau demographics, DCF modeling, rent roll parsing, lease abstraction, and IC memo generation — all from a single prompt.
"Analyze this deal: 2201 South Blvd, Charlotte NC. NOI $400k, asking $6M, retail strip."
→ Pulls live SOFR from the Fed. Pulls Census demographics for that exact block. Builds a full levered 10-year DCF. Writes an institutional-quality IC memo. 30 seconds.
The #1 problem with AI in CRE: 66% of professionals use it daily, but only 5% trust it for actual deal decisions.
The reason? AI guesses at rates and demographics. A DCF built on a hallucinated SOFR rate is worthless.
This MCP fixes that. Every number comes from a verified public source:
Zero data licensing fees. Zero hallucinations on financial inputs.
Prompt: "Get me current interest rates"
Prompt: "Analyze this deal: 2201 South Blvd Charlotte NC, NOI $400k, asking $6M, retail strip"
The MCP automatically chains get_current_rates + get_market_demographics + build_dcf_model + generate_deal_memo and returns a full IC memo including:
Add this to your claude_desktop_config.json and restart Claude Desktop:
If your MCP client only supports stdio servers, use the mcp-remote bridge instead:
Free during beta. All data fetching runs server-side.
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
Restart Claude Desktop. The tools will appear automatically.
Open Claude Desktop and say:
"Get me current interest rates"
You should see it call get_current_rates and return live Federal Reserve data.
The document tools (analyze_rent_roll, abstract_lease) work by pasting PDF text directly into the prompt. In Claude Desktop:
The tool extracts every tenant, suite, SF, rent, lease dates, and expiration into structured JSON — then flag_lease_risks can immediately analyze it for rollover and concentration risk.
MIT
來源：README.md，提交 6e3f241
Get live interest rates from the Federal Reserve (FRED). Returns SOFR, 10-year Treasury, 5-year Treasury, Fed Funds Rate, and 30-day SOFR average. Also calculates implied cap rate ranges based on current treasury spreads. Use this BEFORE any DCF model or loan underwriting. These are real-time numbers Claude cannot access on its own.
無需輸入參數。
Get Census Bureau demographics for any US property address. Returns median income, population, employment rate, housing vacancy, median rents, and education levels for the census tract. This is address-specific data from the actual Census tract — not estimates. Claude cannot access this without the MCP. For 1/3/5-mile trade-area rings, use get_radius_demographics instead.
address必填Get aggregated Census demographics for radius rings around a US property address — the standard 1/3/5-mile trade-area format used in CRE site analysis. Aggregates every census tract whose centroid falls within each radius: population, household-weighted median income, employment rate, college attainment, housing vacancy, renter share, and median rent. Use this for trade-area / site analysis. Use get_market_demographics for the single census tract immediately around the address.
address必填radii_milesScreen a US county as a LAND-INVESTING market (raw-land flip / Podolsky style). Grades the county on the signals that matter for buying cheap rural land and reselling on terms: population growth, demographics, owner share, and affordability. IMPORTANT: This screens on FREE Census data only (growth + demographics + a home-value affordability proxy). It does NOT include actual land sale prices or comps — those require county records or a paid service, and must be verified per-parcel before buying. Use this to rank/shortlist markets, not to buy.
state必填county必填Pre-screen a land parcel's location for the AUTOMATABLE due-diligence red flags: FEMA flood zone and federal wetlands. Pulls live from FEMA's National Flood Hazard Layer and the US Fish & Wildlife National Wetlands Inventory. Use this to kill obviously-bad parcels (flood zone, wetlands) at scale BEFORE spending time on manual due diligence. IMPORTANT: Checks flood + wetlands only. It does NOT check legal ACCESS (landlocked — the #1 land deal-killer), title/liens, or zoning — those stay MANUAL, per-parcel checks via county records. A clean screen here is necessary, NOT sufficient.
lat必填lng必填Get current CPI and rent inflation data from the Federal Reserve. Returns overall inflation, shelter inflation, and rent-specific CPI with YoY changes. Use this to calibrate rent growth assumptions in your DCF model — don't guess.
無需輸入參數。
Get Commercial Real Estate price index and broader market data from the Federal Reserve. Returns CRE price trends, office/retail/industrial vacancy proxies, and credit spreads. Provides macro context for deal underwriting and cap rate analysis.
無需輸入參數。
Extract structured tenant and lease data from a rent roll document. Paste the text content of your rent roll PDF here (copy-paste from PDF reader). Returns tenant list, suite/SF, lease dates, monthly rent, escalations, and options.
text必填property_nameExtract all key terms from a commercial lease document. Returns term, base rent schedule, escalations, TI allowance, CAM structure, renewal options, termination rights, exclusivity, co-tenancy, and red flags.
text必填Analyze a parsed rent roll for investment risks. Feed the output from analyze_rent_roll directly into this tool. Returns: rollover risk, tenant concentration, credit risk, and actionable recommendations.
rent_roll_json必填Build a levered DCF model using live Federal Reserve rates. Automatically fetches current SOFR to derive the loan rate if not provided. Returns: annual cash flows, IRR, equity multiple, cash-on-cash, DSCR, and exit analysis.
loan_ratenoi_year1必填equity_pcthold_yearsexit_cap_ratepurchase_price必填noi_growth_rateamortization_yearsGenerate a formatted CRE acquisition memo / Investment Committee memo. Automatically pulls live rates from FRED and demographics from Census Bureau to provide real market context — not guesses.
noi必填asking_price必填property_type必填property_address必填rent_roll_summaryadditional_contextGenerate a downloadable Excel (.xlsx) underwriting model with LIVE formulas — editable assumptions, PMT/FV amortization, IRR, equity multiple, a sensitivity grid, live Fed rates, and (if an address is given) Census trade-area demographics. Returns a download link valid for 60 minutes.
addressloan_ratenoi_year1必填equity_pcthold_yearsexit_cap_rateproperty_namepurchase_price必填noi_growth_rateamortization_years已滿足適用檢查項的 100%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
SOFR: 3.63% (June 8, 2026)SOFR 30-day: 3.59%10yr Treasury: 4.55%5yr Treasury: 4.29%Fed Funds: 3.63%
Implied cap rates (spread over 10yr T): Core Multifamily: 5.30% – 6.05% Core Industrial: 5.55% – 6.30% Core Office: 6.05% – 7.05% Value-Add: 6.05% – 7.05%
Loan rate guidance: Floating: SOFR + 150–250bps = ~5.38%–5.88% Fixed: 10yr T + 150–200bps = ~6.05%–6.55%Entry Cap Rate: 6.67% (+212bps over 10yr Treasury)Loan Rate: 5.38% (derived from live SOFR 3.63% + 175bps)Year 1 DSCR: 1.53xIRR: 14.6%Equity Multiple: 3.11x
Census Tract demographics (2023 ACS): Median HHI: $141,419 Employment rate: 97.2% College educated: 64.9% Vacancy rate: 8.6%
Recommendation: GO — subject to rent roll review and comp analysis.{ "mcpServers": { "cre-intelligence": { "type": "streamable-http", "url": "https://cre-intelligence-mcp.onrender.com/mcp" } }}{ "mcpServers": { "cre-intelligence": { "command": "npx", "args": ["-y", "mcp-remote", "https://cre-intelligence-mcp.onrender.com/mcp"] } }}git clone https://github.com/Zwondra/cre-intelligence-mcpcd cre-intelligence-mcppython3.11 -m venv venvvenv/bin/pip install -r requirements.txtcp .env.example .env# Add your API keys to .env{ "mcpServers": { "cre-intelligence": { "command": "/path/to/cre-intelligence-mcp/venv/bin/python3", "args": ["/path/to/cre-intelligence-mcp/server.py"], "env": { "ANTHROPIC_API_KEY": "sk-ant-...", "FRED_API_KEY": "your_fred_key", "CENSUS_API_KEY": "your_census_key" } } }}