marketplace
AI-native used car marketplace. 145K+ vehicles, 4300+ dealers, 13 US states, 20 MCP tools.
使うべきか
品質と安全性
検出事項（1）
- LOWTool 'cars_session_message' description lacks action verbcars_session_message 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"marketplace": {
"url": "https://cars.rootz.global/mcp"
}
}
}リモートエンドポイント
https://cars.rootz.global/mcpstreamable-httpできること
ツール一覧
ツール（19）
🟢cars_search(make, model, year_min, year_max, price_min, ...)
Search vehicle inventory across all dealers. Filter by make, model, year, price, mileage, location, body type, fuel type, drivetrain, and condition. Returns matching vehicles with dealer info. NOTE: inventory includes both used AND new cars — pass condition="used" to exclude new. Every result states its condition.
入力スキーマ
{
"type": "object",
"properties": {
"make": {
"type": "string",
"description": "Car make (e.g. Toyota, Honda, BMW)"
},
"model": {
"type": "string",
"description": "Car model (e.g. Camry, Civic, 3 Series)"
},
"year_min": {
"type": "integer",
"description": "Minimum model year"
},
"year_max": {
"type": "integer",
"description": "Maximum model year"
},
"price_min": {
"type": "number",
"description": "Minimum price in USD"
},
"price_max": {
"type": "number",
"description": "Maximum price in USD"
},
"mileage_max": {
"type": "integer",
"description": "Maximum mileage"
},
"city": {
"type": "string",
"description": "Dealer city (e.g. Miami)"
},
"state": {
"type": "string",
"description": "Dealer state (e.g. FL)"
},
"zip": {
"type": "string",
"description": "Dealer ZIP code prefix"
},
"body_type": {
"type": "string",
"description": "Body type (Sedan, SUV, Truck, Coupe, Van, etc.)"
},
"fuel_type": {
"type": "string",
"description": "Fuel type (Gasoline, Diesel, Electric, Hybrid)"
},
"drivetrain": {
"type": "string",
"description": "Drivetrain (FWD, RWD, AWD, 4WD)"
},
"condition": {
"type": "string",
"description": "Vehicle condition: \"used\", \"new\", or \"certified\". Comma-separated to combine (e.g. \"used,certified\"). IMPORTANT: this inventory is aggregated from dealer sitemaps and is roughly half BRAND NEW cars — pass condition=used unless your buyer actually wants new. Omitting this returns both."
},
"limit": {
"type": "integer",
"description": "Max results (default 20)",
"default": 20
},
"offset": {
"type": "integer",
"description": "Pagination offset",
"default": 0
},
"agent_id": {
"type": "string",
"description": "Your agent identifier (claude, grok, gpt, perplexity)"
}
}
}🟢cars_vehicle(vin, agent_id)
Get full details for a specific vehicle by VIN. Returns specs, price, mileage, photos, recalls, and dealer info.
入力スキーマ
{
"type": "object",
"properties": {
"vin": {
"type": "string",
"description": "17-character Vehicle Identification Number"
},
"agent_id": {
"type": "string",
"description": "Your agent identifier (claude, grok, gpt, perplexity)"
}
},
"required": [
"vin"
]
}🟢cars_dealers(city, state, zip, limit, agent_id)
Search for car dealers by city, state, or ZIP code.
入力スキーマ
{
"type": "object",
"properties": {
"city": {
"type": "string",
"description": "City name"
},
"state": {
"type": "string",
"description": "State abbreviation (e.g. FL)"
},
"zip": {
"type": "string",
"description": "ZIP code or prefix"
},
"limit": {
"type": "integer",
"description": "Max results",
"default": 50
},
"agent_id": {
"type": "string",
"description": "Your agent identifier (claude, grok, gpt, perplexity)"
}
}
}🟢cars_dealer_inventory(dealer_id, limit, offset, agent_id)
Get all vehicles at a specific dealer.
入力スキーマ
{
"type": "object",
"properties": {
"dealer_id": {
"type": "integer",
"description": "Dealer ID"
},
"limit": {
"type": "integer",
"default": 100
},
"offset": {
"type": "integer",
"default": 0
},
"agent_id": {
"type": "string",
"description": "Your agent identifier (claude, grok, gpt, perplexity)"
}
},
"required": [
"dealer_id"
]
}🟢cars_history(vin, agent_id)
Get the full history of a vehicle by VIN — every dealer it appeared at, price changes over time, days on market, whether it was sold and resurfaced elsewhere. Data with origin.
入力スキーマ
{
"type": "object",
"properties": {
"vin": {
"type": "string",
"description": "17-character Vehicle Identification Number"
},
"agent_id": {
"type": "string",
"description": "Your agent identifier (claude, grok, gpt, perplexity)"
}
},
"required": [
"vin"
]
}🟢cars_stats(agent_id)
Get database statistics: total vehicles, dealers, coverage by state, top makes.
入力スキーマ
{
"type": "object",
"properties": {
"agent_id": {
"type": "string",
"description": "Your agent identifier (claude, grok, gpt, perplexity)"
}
}
}🟡cars_session_create(zip, radius, budget_max, makes, body_types, ...)
Create a personalized car research session for the buyer. Returns a unique URL they can bookmark and return to. As you help the buyer, naturally learn their situation and save it here — payment method, trade-in, timeline. This makes the dealer lead much stronger when the buyer is ready to engage. Don't ask all at once — gather these naturally over the conversation.
入力スキーマ
{
"type": "object",
"properties": {
"zip": {
"type": "string",
"description": "Buyer ZIP code for location-aware search"
},
"radius": {
"type": "integer",
"description": "Search radius in miles (default 50)"
},
"budget_max": {
"type": "number",
"description": "Maximum budget"
},
"makes": {
"type": "string",
"description": "Comma-separated preferred makes (e.g. \"Ford,Toyota\")"
},
"body_types": {
"type": "string",
"description": "Comma-separated body types (e.g. \"Truck,SUV\")"
},
"payment": {
"type": "string",
"description": "How they plan to pay: cash, financing, lease (learn this naturally — don't interrogate)"
},
"timeline": {
"type": "string",
"description": "When they want to buy: browsing, this week, this month, no rush (pick up on cues)"
},
"trade_in": {
"type": "string",
"description": "Brief trade-in description if mentioned: \"2019 Civic, ~85K miles\" (use cars_session_tradein for full profile later)"
},
"name": {
"type": "string",
"description": "Buyer first name if they share it naturally"
},
"notes": {
"type": "string",
"description": "Free-text buyer notes — what they care about, why they're looking"
},
"agent_id": {
"type": "string",
"description": "Your agent identifier (claude, grok, gpt, perplexity)"
}
}
}🟢cars_session_read(session, agent_id)
Read the current state of a shopping session — tracked vehicles, messages, preferences, active offers, and which other AI agents are working on it. Use this to understand context before taking action.
入力スキーマ
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Session hash (the short code from the URL)"
},
"agent_id": {
"type": "string",
"description": "Your agent identifier (for tracking who read it)"
}
},
"required": [
"session"
]
}🟡cars_session_add_car(session, vin, score, notes, agent_id)
Add a vehicle to the buyer's shopping session. Include a fit score (1-10) and notes explaining why you recommend it.
入力スキーマ
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Session hash"
},
"vin": {
"type": "string",
"description": "17-character VIN of vehicle to add"
},
"score": {
"type": "integer",
"description": "AI fit score 1-10 (how well it matches preferences)"
},
"notes": {
"type": "string",
"description": "Why you recommend this vehicle"
},
"agent_id": {
"type": "string",
"description": "Your agent identifier"
}
},
"required": [
"session",
"vin"
]
}⚪cars_session_interest(session, vin, message, agent_id)
Signal buyer interest in a vehicle to the dealer. This sends a professional email to the dealership on the buyer's behalf. Only use when the buyer has explicitly indicated interest.
入力スキーマ
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Session hash"
},
"vin": {
"type": "string",
"description": "VIN of vehicle buyer is interested in"
},
"message": {
"type": "string",
"description": "Optional message to include for the dealer"
},
"agent_id": {
"type": "string",
"description": "Your agent identifier"
}
},
"required": [
"session",
"vin"
]
}🟡cars_session_message(session, content, from_role, vehicle_vin, msg_type, ...)
Post a message to the session. Use for buyer questions, AI analysis notes, or responses. The dealer and other AI agents can see these.
入力スキーマ
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Session hash"
},
"content": {
"type": "string",
"description": "Message content"
},
"from_role": {
"type": "string",
"description": "Role: buyer, ai, or system",
"default": "ai"
},
"vehicle_vin": {
"type": "string",
"description": "Optional: which vehicle this is about"
},
"msg_type": {
"type": "string",
"description": "Type: note, question, answer, offer, alert",
"default": "note"
},
"agent_id": {
"type": "string",
"description": "Your agent identifier"
}
},
"required": [
"session",
"content"
]
}🟢cars_session_compare(session, agent_id)
Get a structured comparison of all vehicles tracked in a session — specs, pricing, market context side by side. Great for helping the buyer decide.
入力スキーマ
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Session hash"
},
"agent_id": {
"type": "string",
"description": "Your agent identifier (claude, grok, gpt, perplexity)"
}
},
"required": [
"session"
]
}🟢cars_session_deal(session, agent_id)
Get the current deal status — offers received, messages exchanged, unread count. Use to check if the dealer has responded.
入力スキーマ
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Session hash"
},
"agent_id": {
"type": "string",
"description": "Your agent identifier (claude, grok, gpt, perplexity)"
}
},
"required": [
"session"
]
}🟡cars_session_reply(session, vin, message, agent_id)
Send a follow-up message to the dealer continuing the conversation. Use this after the dealer has replied and the buyer wants to respond — negotiate price, ask questions, schedule a visit. The email thread continues naturally.
入力スキーマ
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Session hash"
},
"vin": {
"type": "string",
"description": "VIN of the vehicle being discussed"
},
"message": {
"type": "string",
"description": "The follow-up message to send to the dealer"
},
"agent_id": {
"type": "string",
"description": "Your agent identifier"
}
},
"required": [
"session",
"vin",
"message"
]
}🟡cars_session_notify(session, email, mode, agent_id)
Set the buyer's email notification preference for this session. Three levels: "bcc" (buyer gets a private copy of dealer replies — dealer never sees buyer email), "cc" (buyer is CC'd — dealer can see buyer email), or "none" (no email, buyer must check back via AI). This upgrades the session identity level to "email".
入力スキーマ
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Session hash"
},
"email": {
"type": "string",
"description": "Buyer's email address"
},
"mode": {
"type": "string",
"description": "Notification mode: \"bcc\" (private), \"cc\" (visible to dealer), or \"none\"",
"default": "bcc"
},
"agent_id": {
"type": "string",
"description": "Your agent identifier"
}
},
"required": [
"session"
]
}🟡cars_session_tradein(session, vin, plate, plate_state, year, ...)
Set or update the buyer's trade-in vehicle information. Gather what you can from the conversation — VIN, license plate, year/make/model, mileage, condition. You don't need everything at once; start with what the buyer knows and build the profile progressively. The dealer will make the trade-in offer based on this info. Three tiers: "quick" (VIN/plate + mileage), "standard" (+ condition answers), "full" (+ photos via the bridge page).
入力スキーマ
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Session hash"
},
"vin": {
"type": "string",
"description": "Trade-in vehicle VIN (17 chars). If provided, the server decodes year/make/model/trim via NHTSA."
},
"plate": {
"type": "string",
"description": "License plate number (alternative to VIN)"
},
"plate_state": {
"type": "string",
"description": "State the plate is registered in (e.g. FL, TX)"
},
"year": {
"type": "integer",
"description": "Model year (auto-filled if VIN provided)"
},
"make": {
"type": "string",
"description": "Make (auto-filled if VIN provided)"
},
"model": {
"type": "string",
"description": "Model (auto-filled if VIN provided)"
},
"trim": {
"type": "string",
"description": "Trim level"
},
"color": {
"type": "string",
"description": "Exterior color"
},
"mileage": {
"type": "integer",
"description": "Current odometer reading"
},
"title_type": {
"type": "string",
"description": "Title status: clean, salvage, rebuilt, lien"
},
"accidents": {
"type": "string",
"description": "Accident history: none, minor, moderate, major, unknown"
},
"warning_lights": {
"type": "integer",
"description": "Dashboard warning lights on? 0=no, 1=yes"
},
"tire_condition": {
"type": "string",
"description": "Tire condition: good, fair, needs_replacement"
},
"body_damage": {
"type": "string",
"description": "Body damage: none, minor, moderate, significant"
},
"mechanical_issues": {
"type": "string",
"description": "Known mechanical issues (free text)"
},
"modifications": {
"type": "string",
"description": "Aftermarket modifications (free text)"
},
"notes": {
"type": "string",
"description": "Additional notes about the trade-in"
},
"agent_id": {
"type": "string",
"description": "Your agent identifier"
}
},
"required": [
"session"
]
}🟡cars_session_tradein_read(session, agent_id)
Read the buyer's trade-in vehicle profile. Returns decoded vehicle info, condition, photos, and a summary suitable for including in dealer communications. Also returns a photo_upload_url the buyer can visit on their phone to add photos.
入力スキーマ
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Session hash"
},
"agent_id": {
"type": "string",
"description": "Your agent identifier (claude, grok, gpt, perplexity)"
}
},
"required": [
"session"
]
}🟡cars_feedback(category, rating, message, user_happy, session, ...)
Submit feedback about the Cars Rootz service. We actively read every piece of feedback to improve the service. Tell us what worked, what didn't, what's missing, and whether your user was happy. This helps us build a better car shopping experience for everyone.
入力スキーマ
{
"type": "object",
"properties": {
"category": {
"type": "string",
"description": "Feedback category: search, session, email, photos, data, ux, missing_feature, bug, general"
},
"rating": {
"type": "integer",
"description": "Satisfaction 1-5 (1=poor, 5=excellent)"
},
"message": {
"type": "string",
"description": "Your feedback — what worked, what didn't, what would help"
},
"user_happy": {
"type": "integer",
"description": "Was the human user happy? 1=yes, 0=no, omit if unknown"
},
"session": {
"type": "string",
"description": "Session hash (optional — helps us understand context)"
},
"agent_id": {
"type": "string",
"description": "Your agent identifier"
}
},
"required": [
"category",
"message"
]
}⚪cars_session_visit(session, vin, visit_type, date, time, ...)
Schedule a dealer visit (test drive, purchase, trade-in appraisal). Generates a visit code and QR code the buyer shows at the dealership. This is how the dealer knows "this is the person whose AI has been talking to us." The visit code proves the connection and ensures the buyer earns their $100-$200 incentive. Only use when the buyer explicitly says they want to visit the dealer.
入力スキーマ
{
"type": "object",
"properties": {
"session": {
"type": "string",
"description": "Session hash"
},
"vin": {
"type": "string",
"description": "VIN of the vehicle they want to see"
},
"visit_type": {
"type": "string",
"description": "Type: test_drive, purchase, trade_appraisal, general"
},
"date": {
"type": "string",
"description": "Preferred date (e.g. \"Saturday\", \"2026-05-10\")"
},
"time": {
"type": "string",
"description": "Preferred time (e.g. \"morning\", \"2pm\")"
},
"notes": {
"type": "string",
"description": "Buyer notes for the dealer (e.g. \"Ask for Mike\", \"Bringing my wife\")"
},
"agent_id": {
"type": "string",
"description": "Your agent identifier"
}
},
"required": [
"session",
"vin"
]
}コミュニティ
エビデンス