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.
AI agents invoke build_dcf_model to trigger actions in CRE Intelligence MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
loan_rate | object | — | Loan interest rate % — if None, fetches live SOFR + 175bps |
noi_year1 | number | Yes | Year 1 Net Operating Income ($) |
equity_pct | number | — | Equity as % of purchase price (default 35%) |
hold_years | integer | — | Hold period in years (default 10) |
exit_cap_rate | object | — | Exit cap rate % — if None, uses entry cap + 25bps (conservative) |
purchase_price | number | Yes | Acquisition price ($) |
noi_growth_rate | number | — | Annual NOI growth rate % (default 3.0) |
amortization_years | integer | — | Loan amortization period (default 30 years) |
Parameters from the server's own tool schema.
While the tool performs financial analysis and reads market data, it does not move money, commit financial obligations, or irreversibly alter data. It is fundamentally an Execute category tool because it runs a complex algorithm (DCF modeling) whose outputs depend on input parameters and external data fetches.
From the tool's definition Tool description states it 'Build[s] a levered DCF model' and 'Automatically fetches current SOFR to derive the loan rate' — these are computational operations that execute financial modeling logic with real-world market data inputs.
Attacks that exploit this kind of access
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. It is categorised as a Execute tool in the CRE Intelligence MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
build_dcf_model accepts 8 parameters: loan_rate, noi_year1, equity_pct, hold_years, exit_cap_rate, purchase_price, noi_growth_rate, amortization_years. Required: noi_year1, purchase_price. The full parameter table on this page comes from the server's own tool schema.
Register the CRE Intelligence MCP server in PolicyLayer and add a rule for build_dcf_model: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches CRE Intelligence MCP. Nothing to install.
build_dcf_model is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the build_dcf_model rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for build_dcf_model. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
build_dcf_model is provided by the CRE Intelligence MCP server (Zwondra/cre-intelligence-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →