Moonshot Lab (demo)

Search the SYNTHETIC demo inventory (about 860 fictional vehicles at 20 fictional dealers in TX, CA, FL, GA, AZ, IL, NY and OH). Results are not real vehicles for sale; say so when you show them. Each result has listing_id (dealer_key:VIN), vehicle basics, headline_price (before tax, title and fees), dealer_name, and selling_location: the store that holds the unit, with address and phone. link_status is linked, or ambiguous when the listing does not say which of the dealer's stores holds it (see selling_location_candidates). A unit can be held at a sister store run by another dealer in the same group; operated_by_dealer_id then differs from dealer_id. Matching is exact on vocabularies, so a total of 0 often means a wrong value: check the parameter descriptions, widen radius_miles or drop a filter; a zero total also returns hints. The named parameters are shortcuts. filters reaches every other attribute: for example {"field": "canonical.vin", "op": "eq", "value": "<VIN>"} finds a VIN, {"field": "price_summary.doc_fee", "op": "range", "max": 300}, {"field": "incentives[].label_raw", "op": "eq", "value": "Military Appreciation"}. Payment search: payment_max / payment_min filter on a DEMO monthly finance estimate computed per listing from its itemized out-the-door estimate (tax, title, registration, dealer fees) for the buyer location, minus down payment and trade equity, at a demo APR by credit tier unless apr is given. Each result then has estimated_payment (rounded to $5, with a range) and dealer_advertised_payment when the listing shows one; the response has payment_assumptions and a one-line assumptions_summary to read back to the shopper. For 'under $300/month' pass max_monthly_payment=300. With a cap, near_misses lists up to 3 cars just above it, and a zero result returns to_reach_target (extra down payment, or a 72 or 84 month term). To compare scenarios for one car, use compare_payment_scenarios. Every result has estimated_out_the_door (exact, same as estimate_

Every filterable ontology field (vehicle, listing, store, dealer, price, fee, incentive, media, payment) with its type, range or allowed values, shortcut names, the operators (eq, any_of, contains, range, bool, exists, negate) and example filters for search_inventory. The full compact list is about 30 KB, so narrow it with prefix or query.

Use this to answer 'what would my monthly payment be' for ONE listing. It runs the same itemized out-the-door calculation as estimate_out_the_door (always treated as financed) and turns it into a DEMO monthly finance payment: out-the-door total minus down payment and trade equity, amortized at the APR (or a demo APR by credit_tier) over term_months. Returns finance.estimated_monthly_payment rounded to $5 with monthly_payment_unrounded, monthly_payment_range (rounded outward, so it always contains the unrounded value), financing_eligibility (demo lender rules: minimum amount financed, max term by vehicle age and mileage, with flags), amount_financed_estimate, total_of_payments, finance_charge and every assumption, plus the out-the-door figure it used, a one-line assumptions_summary and any dealer-advertised payment shown separately (not comparable unless the terms match). Totals: total_cost_including_trade_equity (PRIMARY: cash down plus payments plus net trade equity given up) and cash_outlay_excluding_trade_equity (cash down plus payments); total_cost_estimate is a deprecated alias of the latter, kept for one version. For ONE set of terms only: to compare two or more down, term, trade or credit options, call compare_payment_scenarios once instead of calling this tool repeatedly. Use get_price_breakdown instead for the dealer's listed price and fees only, and estimate_out_the_door for the full itemized total without a payment. To find cars by payment across many listings, use search_inventory with max_monthly_payment (canonical; payment_max is a deprecated alias). Estimate, not an offer; dealer sets price, lender sets rate. Not penny-accurate. Leases are not modeled.

Use this to compare several financing what-ifs for ONE listing side by side in one call (for example cash down, term, credit tier or APR, trade-in, incentives). Each scenario reruns the itemized out-the-door estimate and returns estimated_out_the_door, amount_financed_estimate, apr_percent and apr_source, term_months, estimated_monthly_payment (rounded to $5) with the unrounded value and an outward-rounded range, total_interest_estimate, total_cost_including_trade_equity (PRIMARY total: cash down plus all payments plus net trade equity given up), cash_outlay_excluding_trade_equity (cash down plus payments only; total_cost_estimate is its deprecated alias) and financing_eligibility with flags (demo rules), plus lowest_monthly, lowest_total_cost (decided by total_cost_including_trade_equity) and lowest_cash_outlay_excluding_trade_equity. Those lowest_* keys are UNFILTERED math winners. Present recommended_scenario, lowest_monthly_eligible or lowest_total_cost_eligible instead: they skip scenarios the demo financing rules flag, so an ineligible scenario is never the recommendation. A scenario {"name":"cash","cash":true} prices paying cash (no loan, no interest); cash_purchase always gives the cash amount due. Each scenario has trade_risk (negative_equity_rolled_in, loan_to_value_pct and warnings, for example LTV over 110%) and credit_tier_source. Prefer this over repeated get_payment_estimate calls. Up to 6 scenarios. For a single scenario use get_payment_estimate. Estimate, not an offer; dealer sets price, lender sets rate. Leases are not modeled.

Optional and free. Registers your agent and returns an agent key (shown once) that gives it a durable, anonymous id in Moonshot Lab's bot analytics. Send it as the X-MoonshotLab-Agent-Key header, or add ?agent_key=<key> to the MCP URL. Nothing else changes: anonymous use keeps working, limits are the same, and no personal data is collected. Dealers only ever see aggregate demand by platform name.

DEMO. Save a car search and get alerted when new cars match. Returns a search_id (keep it; it is the only way to read or cancel the search) and an expiry (default 30 days, renewable). Check for new cars with get_new_matches, or give a callback_url. Shopper email alerts are optional and need explicit consent. On this demo, email sending is switched off (alerts are logged, not sent) and new arrivals are simulated.

DEMO. New cars that started matching a saved search after it was saved (or after `since`).

DEMO. Cancel a saved search. Any shopper email stored for it is deleted.

Use this when the shopper has picked a car and a deal structure and wants to take it to the dealer. Builds a structured dealer handoff package for ONE configured deal: vehicle and VIN, the full itemized out-the-door estimate (with excluded items such as optional add-ons), the chosen financing scenario with demo financing eligibility, trade and negative-equity details (loan-to-value), all warnings, the assistant name and session reference, a timestamp (UTC and America/Chicago) and an estimate-not-offer disclaimer. Returns the package as JSON plus a ready-to-send email body (email.subject, email.text, email.html) with no recipient filled in. THIS TOOL SENDS NOTHING and contacts no one: delivery.status is not_sent, and delivery happens later, with the shopper's consent, through the dealer's chosen channel (email, desking or F&I). No dealer email is invented; dealer.handoff_contact is null until the dealer provides one. On synthetic data the package is labeled DEMO. Before calling, ask the shopper for a phone number or email for the dealer (with their OK); the call fails without a phone, email, or a name plus preferred_contact. The deal (date, shopper name and contact, car, payment, status) is saved to the store's dealer dashboard, where only that store, its region and group can see the contact info and address. Optional extras the dealer will use: trade_details (VIN, miles, plate, color, who the loan is with and how much), buyer_address (with county, for tax and registration), financing_details (deposit, cash down and rebates as separate lines, and any lender pre-approval the shopper already has) and add_on_interest (yes, no or unsure for service contract, GAP, maintenance, other; never priced). The email has a deal sheet in buyer's order line order including the store's dealer fees. NEVER ask the shopper for a Social Security number (or any part of one), date of birth or income; the tool rejects them. Leases, add-on pricing and payment dates are left to the dealer.

Full synthetic listing record with per-value provenance (method 'synthetic'). listing_id is dealer_key:VIN (as returned by search_inventory) or the urn. The vehicle-to-store link is in listing.selling_location (link_status, selling_location_id, candidates, flags such as group_site_lists_sister_store or multi_store_unstated); the dealer block is the advertising dealer. For price and fees in a compact form, use get_price_breakdown.

Use this to see what the dealer LISTS for ONE listing, as published: headline price, MSRP (new cars), price_components, dealer fees (doc fee and others) and fee bundles (parts marked part_of_bundle, not double counted), flags such as whether the advertised price already includes fees, options, incentives split into all_buyer (already in the price) and conditional (not in the price), and the state's public tax and fee RULES with data-flag checks. It takes no buyer inputs and computes no tax amounts or total. Use estimate_out_the_door next for the buyer's total with tax, title, registration and fees, and get_payment_estimate for a monthly payment. Pass conditional incentive label_raw values to those tools as eligible_incentive_labels only if the shopper qualifies. A dealer-advertised monthly payment, when present, is a price_components item of type payment_quote: dealer ad text, not a calculation. Each price_component has a plain label, source_text and method_text; fees and incentives carry tax_treatment (taxable or reduces_taxable_amount, whether it is inside the advertised price, and why).

Use this for the buyer's TOTAL price of ONE listing: an itemized out-the-door DEMO ESTIMATE for the buyer's state, county and city, built with real public tax and fee rules for the 8 covered states. Lines include the price, dealer fees, eligible incentives, state and local sales tax, title and registration fees, and a trade-in block (allowance, payoff, equity, tax credit). Every line has a source and confidence; unknowns become ranges. Read estimated_out_the_door with estimate_range and confidence. With a trade-in, estimated_out_the_door is the balance due after the trade (negative equity added); deal.vehicle_out_the_door_before_trade is the car alone. Use get_price_breakdown instead for only the dealer's listed price and fees, and get_payment_estimate to turn this total into a monthly finance payment (this tool returns payments: null). Read warnings, for example when the shopper's state differs from the store's state. Not an offer, not a quote, not penny-accurate. Inputs are not stored.

Fictional dealer profile: registry entity, stores (selling locations) with fictional addresses and 555 phone numbers, group, state rules and a page of inventory. Not a real business; do not tell anyone to call or visit.

All 20 fictional demo dealers with group and store counts (each dealer lists its stores with group_id, region_id and store_id), the dealer hierarchy (Group, then Region, then Store), the 4 fictional dealer groups and a coverage summary: which metros have demo stores, with dealer, store and new/used listing counts per metro.

無需輸入參數。

Media block for a listing: self-generated SVG placeholder images labeled DEMO (photo, video poster, spin), with rights notes. They are not photos of a real car. No video or 360 viewer exists in the demo.

Ready-made demo trade-in scenarios (one per state) with trade_value and payoff to pass to estimate_out_the_door or get_payment_estimate.

無需輸入參數。

Schema links, schema version, covered states, condition values, search sorts and the value-wrapper format ({v, m, c, src}). For the list of filterable fields and allowed values, use list_searchable_fields.

無需輸入參數。