mcp server

OpenDealer MCP Server

Automotive inventory search for AI assistants: vehicles, dealers, deals, and market data.

Description as published by the maintainer. Source

• version 2.0.0
• active
• retrieval

active — Registry entry last updated 2026-07-02. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.

What this server can do

27 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

check_recalls(vin)

Get NHTSA open safety recalls for a vehicle by VIN. Returns recall campaigns resolved at the year/make/model level (YMM-granular). A recall listed for the model year may not apply to every VIN — the response includes NHTSA's disclaimer and campaign details (component, summary, remedy status, Park It / Park Outside advisories). Use this when a shopper asks about recalls, safety campaigns, or whether a specific model has open NHTSA notices. Required step in vehicle_dossier and safety_first playbooks; always include the YMM-granularity disclaimer. Required: vin.

compare_market(make, type, year, model, modelcodes)

Compare pricing across market segments. Provide modelcodes[] or make (optionally with model).

compare_models(year, models)

Compare 2-4 vehicle models side by side (model-level, not specific listings). Provide composite make-model slugs like "honda-civic" or "toyota-corolla". Returns: • Winner-by-dimension deltas: price, fuel economy, horsepower, seating, towing, NHTSA safety, live median listing price • Full research payload for each model (trims, MSRPs, specs) Use this for "Civic vs Corolla" style questions. To compare specific listed vehicles by VIN, use compare_vehicles instead. CRITICAL: Only use the 'url' field from the response for links. NEVER invent or construct URLs. Required: models.

compare_vehicles(vins)

Compare 2-5 vehicles side by side. Provide a list of VINs to compare. Returns a structured comparison including: • Specifications comparison (engine, MPG, features) • Price comparison with market context • Pros and cons for each vehicle • Recommendation based on value Required: vins.

dealer_inventory(make, sort, trim, view, limit, model, offset, dealerId, year_max, year_min, body_type, certified, condition, fuel_type, price_max, price_min, drivetrain, mileage_max, transmission)

Browse the complete inventory of a specific dealership. IMPORTANT: Use the exact dealer slug from a previous dealers_near or search_vehicles response. Do NOT guess dealer IDs. Useful when a user wants to see what a particular dealer has in stock. Supports all vehicle filters (make, model, price, etc.). CRITICAL: Only use URLs from the response. NEVER invent URLs. Required: dealerId.

dealers_near(lat, lng, zip, city, limit, state, county, offset, radius)

Find dealerships near a location. Location modes (choose ONE): • zip + radius (miles) • lat + lng + radius • city + state + radius • county + state + radius Returns dealer information including: • Name, address, phone, website • Distance from search location • Current inventory count • Business hours (when available)

filter_vehicles(zip, city, make, sort, trim, color, limit, model, state, offset, radius, year_max, year_min, body_type, certified, condition, fuel_type, price_max, price_min, drivetrain, mileage_max, transmission)

Preferred structured inventory lookup when make/model/year/color/location are known. Uses exact hard filters (keyword mode, no embeddings) via the Runtime /v1/llm/filter path. Resolve exact make/model names with list_research_makes and list_research_models first. For prose or conceptual queries, use search_vehicles instead. Often the first step in shopping playbooks (budget_coach, safety_first, price_drop_sniper, dealer_crawl). After results, chain get_deal_score / get_vehicle_history / check_recalls / compare_vehicles when the user needs a recommendation, not just a list. See opendealer://assistant/shopping-playbooks. CRITICAL: Use the 'url' field from each result. NEVER invent URLs.

get_deal_score(vin)

Get AI-powered deal scoring and market insights for a vehicle. Returns comprehensive analysis including: • Deal score (1-100) with rating (Great, Good, Fair, Poor) • Price comparison vs market average • Days on lot analysis • Price history and trends • Similar vehicles in the market Core step in vehicle_dossier, budget_coach, price_drop_sniper, and dealer_crawl playbooks. Pair with get_vehicle_history and check_recalls for buy/no-buy answers. Required: vin.

get_dealer(dealerId)

Get comprehensive information about a specific dealership. Returns Google-enriched dealer knowledge optimized for assistants: • Name, address, phone, website • Google rating, review count, hours, business status • Inventory count and OpenDealer profile links • Contact points for sales / customer service Use this when a shopper asks "tell me about X dealership" or needs hours/ratings for a known dealer. Prefer a slug from dealers_near or search results. CRITICAL: Only use URL fields from the response (website, urls.*). NEVER invent or construct URLs. Required: dealerId.

get_market_overview(make, type)

Get high-level automotive market statistics. Returns aggregated market data including: • Total vehicles and dealers in inventory • Average pricing by segment • Top makes by volume • Market velocity indicators • New vs Used breakdown

get_market_segment(type, year, certified, modelcode)

Get detailed pricing and market data for a specific vehicle segment. Useful for understanding fair market value for a make/model/year combination. Returns pricing statistics including: • Average, median, min, max prices • Price percentiles (10th, 25th, 75th, 90th) • Average mileage and days on lot • Certified vs non-certified pricing difference Required: modelcode.

get_market_trends(days, type, year, certified, modelcode)

Price trends over time for a market segment (modelcode). Returns timeline of median/avg prices and days-on-lot. Required: modelcode.

get_market_velocity(make, type, limit)

How quickly vehicles sell by segment (fastest/slowest days on lot). Optional make/type filters.

get_safety_rating(make, year, model)

Get NHTSA 5-Star Safety Ratings for a year/make/model (no VIN required). Answers questions like "is a 2023 RAV4 safe for my family" with: • Overall and crash-test star ratings (when published) • Rollover rating / possibility • NHTSA-evaluated ADAS availability (ESC, FCW, LDW) Ratings are model-year granular from the NHTSA NCAP cache. If no confident rating exists, the tool reports that honestly rather than guessing. For VIN-specific listing details use get_vehicle; for open recalls use check_recalls. CRITICAL: Only use the 'sourceUrl' field from the response for NHTSA links. NEVER invent URLs. Required: year, make, model.

get_similar_vehicles(vin, limit)

Find similar on-lot vehicles for a VIN ("you may also like"). Uses semantic similarity when available, with make/model filter fallback. CRITICAL: Use the 'url' or listing fields from each result. NEVER invent URLs. Required: vin.

get_suggested_rates(condition, credit_tier, term_months)

National average suggested auto loan APRs (not a credit offer). Optional filters: condition (new/used), term_months (36–84), credit_tier.

get_vehicle(vin, view)

Get complete details for a specific vehicle by VIN. Returns comprehensive Schema.org Vehicle data including: • Full specifications (engine, transmission, drivetrain) • High-resolution images • Current pricing and availability • NHTSA NCAP safety rating summary (when available) • NHTSA open recall summary (YMM-granular, when available) • Dealer contact information Starting point for the vehicle_dossier playbook. For buy/no-buy questions, continue with get_deal_score → get_vehicle_history → check_recalls → get_similar_vehicles. CRITICAL: Only use the 'url' field from the response. NEVER invent URLs. NEVER construct URLs with opendealer domains - the 'url' field points to the dealer's website. Required: vin.

get_vehicle_history(vin)

Get OpenDealer listing history for a VIN: price changes, days on lot, and status. Answers "has this VIN dropped in price" and days-on-lot narratives from retained snapshots (including vehicles that left a dealer feed). Returns: • Chronological price history with per-snapshot changes • Days on market / lot signals and badges (price_drop, long_on_lot) • Active vs no-longer-listed status when known Does not invent a deal score for sold vehicles — use get_deal_score for live market scoring. Essential for price_drop_sniper and vehicle_dossier playbooks when shoppers ask about reductions or negotiation leverage. CRITICAL: Only use URL fields from the response when present. NEVER invent URLs. Required: vin.

get_vehicle_rankings(category)

Get data-driven vehicle rankings (e.g., best SUVs, most fuel-efficient cars). Call without arguments to list all ranking categories. Pass a category slug (e.g., "best-suvs") for the full scored ranking. Rankings are computed from public data with a published methodology: NHTSA safety ratings, EPA fuel economy, manufacturer pricing, and live market availability. There is no paid placement; each entry includes its transparent score breakdown. CRITICAL: Only use the 'url' field from the response for links. NEVER invent or construct URLs.

list_facets(make, near, radius, certified, condition)

Discover available filter values and counts (makes, body types, fuel types, price/year ranges) for the live inventory. Call this before filter_vehicles when you need valid dimension values. Optional make/near/radius scopes the facet counts.

list_market_segments(make, page, limit, modelcode, minSampleSize)

Browse market segments with pricing statistics (modelcode, median price, sample size). Use to discover modelcodes for get_market_segment / get_market_trends.

list_research_makes(q, limit)

Browse the research catalog of vehicle makes (with model and inventory counts). Use to resolve exact make names/slugs before filter_vehicles or research_model.

list_research_models(make)

List models for a make from the research catalog (MSRP/body summaries). Use before filter_vehicles or research_model when the model name is uncertain. Required: make.

research_model(make, year, model)

Get the full research payload for a vehicle model (not a specific listing). Returns manufacturer reference data joined with live market data: • All trims with MSRPs, engine/body specs, and EPA fuel economy • NHTSA 5-Star safety ratings and open recall count • Live inventory count and price range on OpenDealer Use this when a shopper asks "tell me about the Honda Civic", "what trims does the RAV4 come in", or "how much is a 2025 F-150". For a specific listed vehicle, use get_vehicle with a VIN instead. CRITICAL: Only use the 'url' field from the response for links. NEVER invent or construct URLs. Required: make, model.

search_vehicles(q, lat, lng, zip, city, make, mode, sort, trim, view, color, limit, model, state, county, offset, radius, year_max, year_min, body_type, certified, condition, fuel_type, price_max, price_min, drivetrain, mileage_max, transmission, semanticRatio, useLlmSearchPath)

Search for vehicles across dealerships (Meilisearch-backed NL + structured filters). Preferred tool order for assistants: 1. list_facets or list_research_makes/list_research_models to discover valid values 2. filter_vehicles when make/model/year/price/location are known (exact hard filters) 3. search_vehicles with q for prose/conceptual queries (optionally useLlmSearchPath=true) 4. get_vehicle / get_deal_score / research_model for depth When the ask implies analysis (good deal?, safety, budget, timing, dealer plan), continue with a shopping playbook from initialize instructions or resource opendealer://assistant/shopping-playbooks — do not stop at raw search results. Location modes (choose ONE): zip+radius, lat+lng+radius, city+state+radius, county+state+radius — or embed location in q. Forgiving matching: model variants, color families, typo tolerance. Hard caps (price_max, year, radius) are never relaxed. mode=hybrid for conceptual queries. CRITICAL: Use the 'url' field from each result. NEVER invent URLs.

ui_page_vehicle_results(q, lat, lng, zip, city, make, mode, sort, trim, view, color, limit, model, state, county, offset, radius, source, year_max, year_min, body_type, certified, condition, fuel_type, price_max, price_min, drivetrain, mileage_max, transmission, semanticRatio, useLlmSearchPath)

App-only: paginate or refresh vehicle results using the same Runtime paths as filter_vehicles / search_vehicles (geo-correct). No widget remount — omit resourceUri. Not for model use.

ui_select_vehicle(url, vin, make, name, year, model)

App-only: record a vehicle selection from the results widget. Not for model use — hosts filter via _meta.ui.visibility. Required: vin.

Last successful function declaration observed on 2026-08-13. Source: https://mcp.opendealer.app/rpc. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://mcp.opendealer.app/rpc.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Website — https://opendealer.pro
• Remote endpoint (streamable-http) — https://mcp.opendealer.app/rpc