{
  "markdown": "# CRE Intelligence MCP\n\n**Live market data for commercial real estate analysis — inside Claude.**\n\nConnect 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.\n\n> *\"Analyze this deal: 2201 South Blvd, Charlotte NC. NOI $400k, asking $6M, retail strip.\"*\n>\n> → 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.**\n\n---\n\n## Why this exists\n\nThe #1 problem with AI in CRE: **66% of professionals use it daily, but only 5% trust it for actual deal decisions.**\n\nThe reason? AI guesses at rates and demographics. A DCF built on a hallucinated SOFR rate is worthless.\n\nThis MCP fixes that. Every number comes from a verified public source:\n- **Interest rates** → Federal Reserve (FRED API)\n- **Demographics** → US Census Bureau ACS\n- **Document analysis** → Claude AI with structured output\n\nZero data licensing fees. Zero hallucinations on financial inputs.\n\n---\n\n## Tools\n\n| Tool | What it does | Data source |\n|------|-------------|-------------|\n| `get_current_rates` | Live SOFR, 10yr Treasury, Fed Funds + implied cap ranges by property type | FRED |\n| `get_inflation_data` | CPI, shelter inflation, rent CPI + DCF rent growth guidance | FRED |\n| `get_cre_market_data` | CRE price index, C&I loan trends, delinquency rates, credit spreads | FRED |\n| `get_market_demographics` | Median income, employment, vacancy, rents for any US address | Census Bureau |\n| `get_radius_demographics` | 1/3/5-mile trade-area rings: population, weighted income, renter share, rents | Census Bureau |\n| `analyze_rent_roll` | Paste PDF text → structured JSON: tenant, SF, rent, dates, expirations | Claude AI |\n| `abstract_lease` | Paste lease text → term, rent schedule, TI, options, red flags | Claude AI |\n| `flag_lease_risks` | Rent roll JSON → rollover risk, concentration risk, due diligence checklist | Claude AI |\n| `build_dcf_model` | Full levered 10-year DCF with live rates auto-fetched from FRED | Python + FRED |\n| `generate_deal_memo` | Address + NOI + price → full IC memo with live rates and demographics | Claude AI + FRED + Census |\n| `export_dcf_excel` | Downloadable .xlsx underwriting model with live formulas, sensitivity grid, market data | Python + FRED + Census |\n\n---\n\n## Example output\n\n**Prompt:** *\"Get me current interest rates\"*\n\n```\nSOFR:           3.63%   (June 8, 2026)\nSOFR 30-day:    3.59%\n10yr Treasury:  4.55%\n5yr Treasury:   4.29%\nFed Funds:      3.63%\n\nImplied cap rates (spread over 10yr T):\n  Core Multifamily:  5.30% – 6.05%\n  Core Industrial:   5.55% – 6.30%\n  Core Office:       6.05% – 7.05%\n  Value-Add:         6.05% – 7.05%\n\nLoan rate guidance:\n  Floating: SOFR + 150–250bps = ~5.38%–5.88%\n  Fixed:    10yr T + 150–200bps = ~6.05%–6.55%\n```\n\n**Prompt:** *\"Analyze this deal: 2201 South Blvd Charlotte NC, NOI $400k, asking $6M, retail strip\"*\n\nThe MCP automatically chains `get_current_rates` + `get_market_demographics` + `build_dcf_model` + `generate_deal_memo` and returns a full IC memo including:\n\n```\nEntry Cap Rate:   6.67%  (+212bps over 10yr Treasury)\nLoan Rate:        5.38%  (derived from live SOFR 3.63% + 175bps)\nYear 1 DSCR:      1.53x\nIRR:              14.6%\nEquity Multiple:  3.11x\n\nCensus Tract demographics (2023 ACS):\n  Median HHI:       $141,419\n  Employment rate:  97.2%\n  College educated: 64.9%\n  Vacancy rate:     8.6%\n\nRecommendation: GO — subject to rent roll review and comp analysis.\n```\n\n---\n\n## Setup\n\n### Option A — Hosted (fastest, no API keys)\n\nAdd this to your `claude_desktop_config.json` and restart Claude Desktop:\n\n```json\n{\n  \"mcpServers\": {\n    \"cre-intelligence\": {\n      \"type\": \"streamable-http\",\n      \"url\": \"https://cre-intelligence-mcp.onrender.com/mcp\"\n    }\n  }\n}\n```\n\nIf your MCP client only supports stdio servers, use the `mcp-remote` bridge instead:\n\n```json\n{\n  \"mcpServers\": {\n    \"cre-intelligence\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"mcp-remote\", \"https://cre-intelligence-mcp.onrender.com/mcp\"]\n    }\n  }\n}\n```\n\nFree during beta. All data fetching runs server-side.\n\n### Option B — Self-hosted\n\n#### Prerequisites\n- [Claude Desktop](https://claude.ai/download)\n- Python 3.11+\n- Free API keys (takes ~2 minutes total):\n  - **FRED:** [fred.stlouisfed.org/docs/api/api_key.html](https://fred.stlouisfed.org/docs/api/api_key.html)\n  - **Census:** [api.census.gov/data/key_signup.html](https://api.census.gov/data/key_signup.html)\n  - **Anthropic:** [console.anthropic.com](https://console.anthropic.com)\n\n#### Install\n\n```bash\ngit clone https://github.com/Zwondra/cre-intelligence-mcp\ncd cre-intelligence-mcp\npython3.11 -m venv venv\nvenv/bin/pip install -r requirements.txt\ncp .env.example .env\n# Add your API keys to .env\n```\n\n### Connect to Claude Desktop\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"cre-intelligence\": {\n      \"command\": \"/path/to/cre-intelligence-mcp/venv/bin/python3\",\n      \"args\": [\"/path/to/cre-intelligence-mcp/server.py\"],\n      \"env\": {\n        \"ANTHROPIC_API_KEY\": \"sk-ant-...\",\n        \"FRED_API_KEY\": \"your_fred_key\",\n        \"CENSUS_API_KEY\": \"your_census_key\"\n      }\n    }\n  }\n}\n```\n\nRestart Claude Desktop. The tools will appear automatically.\n\n### Test it\n\nOpen Claude Desktop and say:\n\n> *\"Get me current interest rates\"*\n\nYou should see it call `get_current_rates` and return live Federal Reserve data.\n\n---\n\n## Document analysis\n\nThe document tools (`analyze_rent_roll`, `abstract_lease`) work by pasting PDF text directly into the prompt. In Claude Desktop:\n\n1. Open your rent roll or lease PDF\n2. Copy all the text\n3. Say: *\"Analyze this rent roll: [paste text]\"*\n\nThe 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.\n\n---\n\n## Data sources\n\n| Source | What | Cost |\n|--------|------|------|\n| [FRED (Federal Reserve)](https://fred.stlouisfed.org) | SOFR, Treasury yields, Fed Funds, CPI, CRE price index | Free |\n| [Census Bureau ACS](https://www.census.gov/data/developers/data-sets/acs-5year.html) | Income, employment, housing, rents by census tract | Free |\n| [Anthropic Claude](https://anthropic.com) | Document parsing, risk analysis, memo generation | Pay per use |\n\n---\n\n## Roadmap\n\n- [ ] Comparable sales search (CREXI public listings)\n- [ ] Multi-property portfolio analysis\n- [ ] Sensitivity table generation (cap rate / NOI / LTV scenarios)\n- [ ] Export to Excel / Word\n- [ ] Deal history / comparison across sessions\n\n---\n\n## License\n\nMIT\n",
  "bytes": 6764,
  "sha": "c93f4dcd71ac692f3113056749d9d9d9afc256833061a93494fb6a81d1d09716",
  "repo_slug": "zwondra/cre-intelligence-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_zwondra_cre_intelligence_mcp_b9711e57/readme"
}