About OpenDealer MCP Server
Automotive inventory search for AI assistants: vehicles, dealers, deals, and market data
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
Endpoint
https://mcp.opendealer.app/rpcCopy install command
Claude CodeTerminal
claude mcp add --transport http app-opendealer https://mcp.opendealer.app/rpcCursor.cursor/mcp.json
{"mcpServers":{"app-opendealer":{"type":"http","url":"https://mcp.opendealer.app/rpc"}}}Open in CursorVS Code.vscode/mcp.json
{"servers":{"app-opendealer":{"type":"http","url":"https://mcp.opendealer.app/rpc"}}}Open in VS CodeClaude Desktopclaude_desktop_config.json
{"mcpServers":{"app-opendealer":{"type":"http","url":"https://mcp.opendealer.app/rpc"}}}Windsurf~/.codeium/windsurf/mcp_config.json
{"mcpServers":{"app-opendealer":{"serverUrl":"https://mcp.opendealer.app/rpc"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
All endpoints
Streamable HTTP
https://mcp.opendealer.app/rpcAuth requiredTools
27| Parameter | Type | Required | Description |
|---|---|---|---|
| q | string | No | Free-text natural-language query, or a 17-character VIN for exact listing lookup. For sentences (e.g. "new black Honda Civic sedan under $45k within 150 miles of 92672"), price/mileage/year/condition and zip+radius are parsed as hard constraints; make/model/color/body words are matched forgivingly. Explicit structured params override parsed values. Prefer filter_vehicles when make/model/location are already known. |
| lat | number | No | Latitude coordinate |
| lng | number | No | Longitude coordinate |
| zip | string | No | 5-digit US ZIP code (e.g., 92688) |
| city | string | No | City name |
| make | string | No | Vehicle make (e.g., Honda, Toyota, Tesla) |
| mode | enum | No | Search mode. Use hybrid for conceptual queries with little keyword overlap (e.g. "family hauler good in snow"). Hard caps still apply as filters. Falls back to keyword if semantic is unavailable.keyword | hybrid |
| sort | enum | No | Sort order for resultsrelevance | price_asc | price_desc | year_desc | mileage_asc | distance_asc |
| trim | string | No | Trim level (e.g., EX, Limited, Performance) |
| view | enum | No | Response format: llm (optimized for AI), standard (full details), minimal (compact)llm | standard | minimal |
| color | string | No | Exterior color (e.g., black, white). Resolved to color families, so "black" matches "Crystal Black Pearl". |
| limit | integer | No | Maximum number of results to return (1-100, default: 25) |
| model | string | No | Vehicle model (e.g., Civic, Camry, Model 3). Broad terms match all variants (Civic -> Civic Sedan/Si/Hatchback) unless narrowed by trim. |
| state | string | No | 2-letter US state code (e.g., CA, TX) |
| county | string | No | County name |
| offset | integer | No | Number of results to skip. The window is the next `limit` vehicles starting at this offset (default 0). |
| radius | integer | No | Search radius in miles (1-250). Omit to use the platform default of 150 miles, the same as the shop and the Runtime API. |
| year_max | integer | No | Maximum model year |
| year_min | integer | No | Minimum model year |
| body_type | enum | No | Vehicle body styleSedan | SUV | Truck | Coupe | Van | Wagon | Convertible | Hatchback |
| certified | boolean | No | Filter for Certified Pre-Owned vehicles only |
| condition | enum | No | Vehicle conditionNew | Used | Certified |
| fuel_type | enum | No | Fuel typeGasoline | Diesel | Electric | Hybrid | Plug-in Hybrid |
| price_max | integer | No | Maximum price in USD |
| price_min | integer | No | Minimum price in USD |
| drivetrain | enum | No | Drivetrain configurationFWD | RWD | AWD | 4WD |
| mileage_max | integer | No | Maximum mileage |
| transmission | enum | No | Transmission typeAutomatic | Manual | CVT |
| semanticRatio | number | No | Semantic blend weight 0..1 when mode=hybrid (default 0.5). Higher = more conceptual matching. |
| useLlmSearchPath | boolean | No | Legacy. Do not set. Prefer filter_vehicles with labeled hard filters. |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
Markdown supported
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.