Cardog

Official5 toolsLive

by cardog-ai

VIN decode, Canadian listings, market quotes, TC+NHTSA recalls. Full API: https://cardog.app/docs.md

Cardog MCP Server (app.cardog/mcp)

The Cardog MCP server connects Model Context Protocol (MCP) clients to automotive data, including VIN decode, Canadian listings, market quotes, and TC+NHTSA recall information. Its full API documentation is available at https://cardog.app/docs.md, and it runs over an SSE server URL.

🛠️ Key Features

VIN decode
Canadian listings
Market quotes
TC+NHTSA recalls
Tool count: 5

🚀 Use Cases

Retrieve structured vehicle information from a VIN
Look up Canadian listings for vehicles
Get market quote data for vehicles
Check TC+NHTSA recall details

⚡ Developer Benefits

Integrates AI applications via MCP (SSE endpoint)
Uses developer-facing API documentation at the provided docs URL
Provides setup guidance for Claude Code and Claude Desktop

⚠️ Limitations

Server access requires an API key (obtainable from cardog.app/account/api)
Readme excerpt includes Claude Code/Desktop setup, without other client compatibility details

Captured live from the server via tools/list.

resolve_entity

Turn free text into canonical Cardog entity refs — THE text entry point for every other tool. A ref is `{domain}:{key}`, lowercase, with `/` separating composite key segments: "make:tesla", "model:mini/hardtop", "model-year:honda/cr-v/2026", "fuel-type:electric". (Exception: nano/squish keys are uppercase VIN charset — machine-derived, never typed from text.) Every other tool takes refs, never names. Call this FIRST whenever you hold text — "Civic", "2024 Model Y", a misspelling like "teslla" — then reuse the refs for the rest of the session. Returns candidates with confidence, best-first. `best` is the top candidate ONLY when it clears the confidence floor; otherwise it is null and YOU choose from `candidates` (or ask the user) — the API never guesses. Pass `domain` to constrain the search (use domain "model-year" when you need a market_quote instrument). Errors are instructions: every failure returns {code, message, hint, suggestions} — follow `hint` for the next call; `suggestions` lists nearest valid refs for a bad ref. Unknown-but-well-formed refs are a 400 naming the ref, NEVER a silent fuzzy match. Next steps (also echoed in each result's `next` block): search_inventory with make/model refs; market_quote with a model-year: ref; check_recalls with any make/model/model-year ref; dereference a ref (parents, children, counts) at GET /v2/entities/{ref}.

Parameters4

query	string	required	Free text to resolve, e.g. "2021 Civic", "teslla", "plug-in hybrid"
domain	string	optional	Constrain candidates to one domain: "make", "model", "model-year", "body-style", "fuel-type", "drive-type", "transmission", "electrification-level", "vehicle-type". Omit to search across domains.
limit	integer	optional	Max candidates (default 5)
context	string	required	Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization."

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "description": "Free text to resolve, e.g. \"2021 Civic\", \"teslla\", \"plug-in hybrid\""
    },
    "domain": {
      "type": "string",
      "description": "Constrain candidates to one domain: \"make\", \"model\", \"model-year\", \"body-style\", \"fuel-type\", \"drive-type\", \"transmission\", \"electrification-level\", \"vehicle-type\". Omit to search across domains."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 10,
      "description": "Max candidates (default 5)"
    },
    "context": {
      "type": "string",
      "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\""
    }
  },
  "required": [
    "query",
    "context"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

identify_vehicle

Decode a 17-character VIN into its full Cardog identity: canonical entity refs, the market grains (nano/squish), spec highlights, and links to adjacent resources. VIN ONLY — this tool never fuzzy-matches. If you hold free text ("2021 Civic", a make or model name), do NOT call this: call resolve_entity — free text enters the platform in exactly one tool. A non-VIN input returns a redirect hint, not a decode. A ref is `{domain}:{key}`, lowercase, with `/` separating composite key segments: "make:tesla", "model:mini/hardtop", "model-year:honda/cr-v/2026", "fuel-type:electric". (Exception: nano/squish keys are uppercase VIN charset — machine-derived, never typed from text.) The result's `refs` block (make/model/modelYear/fuelType/…) contains the join keys for every other tool; a null ref means "not derivable for this VIN", never "unknown ref". `squish` (WMI+VDS+year) is always derivable and is a valid market_quote instrument; `nano` is the fungible build grain for dedup/comparables. `specHighlights` is a best-effort skim of the canonical spec sheet (horsepower, economy, range, seating…) — the full sheet lives at GET /v2/specs/{refs.modelYear}. Errors are instructions: every failure returns {code, message, hint, suggestions} — follow `hint` for the next call; `suggestions` lists nearest valid refs for a bad ref. Unknown-but-well-formed refs are a 400 naming the ref, NEVER a silent fuzzy match. Next: check_recalls({ vin }) — outstanding recalls; market_quote({ ref: refs.modelYear ?? squish }); search_inventory({ models: [refs.model] }).

Parameters2

vin	string	required	The 17-character VIN. Free text is NOT accepted here — use resolve_entity for text.
context	string	required	Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization."

Raw schema

{
  "type": "object",
  "properties": {
    "vin": {
      "type": "string",
      "minLength": 1,
      "description": "The 17-character VIN. Free text is NOT accepted here — use resolve_entity for text."
    },
    "context": {
      "type": "string",
      "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\""
    }
  },
  "required": [
    "vin",
    "context"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

search_inventory

Search live Canadian vehicle listings — ref-native. One call returns listings + facets + the total count. Filters take entity REFS from resolve_entity / identify_vehicle, never free-text names: makes: ["make:mini"], models: ["model:mini/hardtop"], fuelTypes: ["fuel-type:electric"] — plus year/price/odometer ranges and canonical spec filters, e.g. spec: {"fuelEconomyCombined": {"min": 35}, "heatedSeatsFront": ["standard"]} (numeric attrs take {min,max}; equipment attrs take ["standard"|"optional"|"unavailable"]). A ref is `{domain}:{key}`, lowercase, with `/` separating composite key segments: "make:tesla", "model:mini/hardtop", "model-year:honda/cr-v/2026", "fuel-type:electric". (Exception: nano/squish keys are uppercase VIN charset — machine-derived, never typed from text.) Errors are instructions: every failure returns {code, message, hint, suggestions} — follow `hint` for the next call; `suggestions` lists nearest valid refs for a bad ref. Unknown-but-well-formed refs are a 400 naming the ref, NEVER a silent fuzzy match. A typo'd or unknown ref 400s with code "unknown_entity_refs" naming it, with nearest-ref suggestions — correct the ref (usually via resolve_entity) and retry. Facets in the result are (ref, name, count) buckets over the MATCHING set — they double as the valid filter vocabulary for your next, narrower call. Every listing row carries its refs (makeRef/modelRef/nano). Next: market_quote({ ref: "model-year:…" }) for pricing context; check_recalls({ vin }) per listing; GET /v2/listings/vin/{vin} for the full canonical spec.

Parameters17

makes	array	optional	Entity refs in the "make" domain, e.g. ["make:mini"]
models	array	optional	Entity refs in the "model" domain, e.g. ["model:mini/hardtop"]
bodyStyles	array	optional	Entity refs in the "body-style" domain, e.g. ["body-style:sport-utility-vehicle-suv"]
fuelTypes	array	optional	Entity refs in the "fuel-type" domain, e.g. ["fuel-type:electric"]
driveTypes	array	optional	Entity refs in the "drive-type" domain, e.g. ["drive-type:awd-all-wheel-drive"]
transmissions	array	optional	Entity refs in the "transmission" domain, e.g. ["transmission:automatic"]
electrificationLevels	array	optional	Entity refs in the "electrification-level" domain, e.g. ["electrification-level:bev-battery-electric-vehicle"]
vehicleTypes	array	optional	Entity refs in the "vehicle-type" domain, e.g. ["vehicle-type:passenger-car"]
nanos	array	optional	Entity refs in the "nano" domain, e.g. ["nano:5TDGSKFCRS"]
year	object	optional	Model year range
price	object	optional	Price (CAD) range
odometer	object	optional	Odometer (km) range
spec	object	optional	Canonical spec filters keyed by SpecAttributeId: numeric → {"min","max"}, equipment → ["standard"\|"optional"\|"unavailable"]. Example: {"fuelEconomyCombined": {"min": 35}, "heatedSeatsFront": ["standard"]}. Bare scalars are invalid — "standard" must be ["standard"]; a wrong-shaped value errors with code "invalid_spec_filter". Unknown keys 400 with code "unknown_spec_attributes".
sort	object	optional
page	integer	optional	Page number (default 1)
limit	integer	optional	Rows per page (default 10, max 50)
context	string	required	Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization."

Raw schema

{
  "type": "object",
  "properties": {
    "makes": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Entity refs in the \"make\" domain, e.g. [\"make:mini\"]"
    },
    "models": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Entity refs in the \"model\" domain, e.g. [\"model:mini/hardtop\"]"
    },
    "bodyStyles": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Entity refs in the \"body-style\" domain, e.g. [\"body-style:sport-utility-vehicle-suv\"]"
    },
    "fuelTypes": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Entity refs in the \"fuel-type\" domain, e.g. [\"fuel-type:electric\"]"
    },
    "driveTypes": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Entity refs in the \"drive-type\" domain, e.g. [\"drive-type:awd-all-wheel-drive\"]"
    },
    "transmissions": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Entity refs in the \"transmission\" domain, e.g. [\"transmission:automatic\"]"
    },
    "electrificationLevels": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Entity refs in the \"electrification-level\" domain, e.g. [\"electrification-level:bev-battery-electric-vehicle\"]"
    },
    "vehicleTypes": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Entity refs in the \"vehicle-type\" domain, e.g. [\"vehicle-type:passenger-car\"]"
    },
    "nanos": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Entity refs in the \"nano\" domain, e.g. [\"nano:5TDGSKFCRS\"]"
    },
    "year": {
      "type": "object",
      "properties": {
        "min": {
          "type": "number"
        },
        "max": {
          "type": "number"
        }
      },
      "additionalProperties": false,
      "description": "Model year range"
    },
    "price": {
      "type": "object",
      "properties": {
        "min": {
          "type": "number"
        },
        "max": {
          "type": "number"
        }
      },
      "additionalProperties": false,
      "description": "Price (CAD) range"
    },
    "odometer": {
      "type": "object",
      "properties": {
        "min": {
          "type": "number"
        },
        "max": {
          "type": "number"
        }
      },
      "additionalProperties": false,
      "description": "Odometer (km) range"
    },
    "spec": {
      "type": "object",
      "additionalProperties": {},
      "description": "Canonical spec filters keyed by SpecAttributeId: numeric → {\"min\",\"max\"}, equipment → [\"standard\"|\"optional\"|\"unavailable\"]. Example: {\"fuelEconomyCombined\": {\"min\": 35}, \"heatedSeatsFront\": [\"standard\"]}. Bare scalars are invalid — \"standard\" must be [\"standard\"]; a wrong-shaped value errors with code \"invalid_spec_filter\". Unknown keys 400 with code \"unknown_spec_attributes\"."
    },
    "sort": {
      "type": "object",
      "properties": {
        "field": {
          "type": "string",
          "enum": [
            "price",
            "year",
            "odometer",
            "createdAt",
            "score"
          ]
        },
        "direction": {
          "type": "string",
          "enum": [
            "asc",
            "desc"
          ]
        }
      },
      "additionalProperties": false
    },
    "page": {
      "type": "integer",
      "minimum": 1,
      "description": "Page number (default 1)"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "description": "Rows per page (default 10, max 50)"
    },
    "context": {
      "type": "string",
      "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\""
    }
  },
  "required": [
    "context"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

market_quote

The live market card for one instrument: quote (live listing count, best/p25/median/p75 price, average days-on-market, 30-day price cuts), a daily-bar history summary, and a bounded sample of the live listings behind the numbers. `ref` must be an INSTRUMENT ref — one of two grains: - "model-year:{make}/{model}/{year}" (e.g. "model-year:honda/cr-v/2026") — lowercase, /-separated; get it from resolve_entity (domain "model-year") or identify_vehicle's refs.modelYear. - "squish:{9 uppercase VIN chars}" (e.g. "squish:5TDGSKFCS") — the exact-config grain; get it from identify_vehicle. (squish/nano keys are the ONLY uppercase refs; every other domain is lowercase.) No other ref domain quotes. Errors are instructions: every failure returns {code, message, hint, suggestions} — follow `hint` for the next call; `suggestions` lists nearest valid refs for a bad ref. Unknown-but-well-formed refs are a 400 naming the ref, NEVER a silent fuzzy match. Optional `window` picks the history span: 1w, 1m, 3m, 6m, ytd, 1y, 3y, 5y, 10y, all. Next: search_inventory with the model's refs to walk the full book; check_recalls({ ref }) on a model-year ref; GET /v2/tape/history/{ref} for every daily bar.

Parameters3

ref	string	required	Instrument ref: "model-year:honda/cr-v/2026" or "squish:5TDGSKFCS". Free text never quotes — resolve_entity first.
window	string	optional	History window (server default when omitted)
context	string	required	Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization."

Raw schema

{
  "type": "object",
  "properties": {
    "ref": {
      "type": "string",
      "minLength": 1,
      "description": "Instrument ref: \"model-year:honda/cr-v/2026\" or \"squish:5TDGSKFCS\". Free text never quotes — resolve_entity first."
    },
    "window": {
      "type": "string",
      "enum": [
        "1w",
        "1m",
        "3m",
        "6m",
        "ytd",
        "1y",
        "3y",
        "5y",
        "10y",
        "all"
      ],
      "description": "History window (server default when omitted)"
    },
    "context": {
      "type": "string",
      "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\""
    }
  },
  "required": [
    "ref",
    "context"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

check_recalls

The authoritative "is this vehicle under recall?" check — Transport Canada + NHTSA recall campaigns, fused and ref-keyed. Compliance guide: https://cardog.app/docs/compliance. Pass EXACTLY ONE of: - `vin` (17 characters) — the per-vehicle recall check. In the result, `resolved: false` means the VIN is not bridged into the graph yet — distinct from "no recalls" (`resolved: true, total: 0`). - `ref` — an entity ref scoping campaigns: "make:honda", "model:honda/cr-v", or "model-year:honda/cr-v/2026". A ref is `{domain}:{key}`, lowercase, with `/` separating composite key segments: "make:tesla", "model:mini/hardtop", "model-year:honda/cr-v/2026", "fuel-type:electric". (Exception: nano/squish keys are uppercase VIN charset — machine-derived, never typed from text.) Get refs from resolve_entity or identify_vehicle — never construct them from guessed names. Each campaign carries: authority (tc/nhtsa) + campaign number, component, defect/consequence summaries, the corrective action, recall date, units affected, and `affects` — the affected model-years as refs. `asOf` (VIN checks) is when the recall data was last updated, citable. Errors are instructions: every failure returns {code, message, hint, suggestions} — follow `hint` for the next call; `suggestions` lists nearest valid refs for a bad ref. Unknown-but-well-formed refs are a 400 naming the ref, NEVER a silent fuzzy match. Next: identify_vehicle({ vin }) for the vehicle's full identity; market_quote({ ref: "model-year:…" }); GET /v2/recalls/{recall-ref} for one campaign; GET /v2/recalls/feed for the newest campaigns.

Parameters4

vin	string	optional	17-character VIN — the per-vehicle recall check. Exclusive with `ref`.
ref	string	optional	Entity ref scope: "make:honda", "model:honda/cr-v", or "model-year:honda/cr-v/2026". Exclusive with `vin`.
limit	integer	optional	Max campaigns for a ref-scoped query (default 25, max 100)
context	string	required	Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization."

Raw schema

{
  "type": "object",
  "properties": {
    "vin": {
      "type": "string",
      "description": "17-character VIN — the per-vehicle recall check. Exclusive with `ref`."
    },
    "ref": {
      "type": "string",
      "description": "Entity ref scope: \"make:honda\", \"model:honda/cr-v\", or \"model-year:honda/cr-v/2026\". Exclusive with `vin`."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "description": "Max campaigns for a ref-scoped query (default 25, max 100)"
    },
    "context": {
      "type": "string",
      "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\""
    }
  },
  "required": [
    "context"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

README.md3 KBView on GitHub

Cardog MCP Server

Connect AI applications to automotive data through the Model Context Protocol.

Server URL: https://mcp.cardog.io/sse

Quick Start

Claude Code

bash

claude mcp add cardog https://mcp.cardog.io/sse --transport sse

Enter your API key when prompted. Get one at cardog.app/account/api.

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

json

{
  "mcpServers": {
    "cardog": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.cardog.io/sse?api_key=YOUR_API_KEY"]
    }
  }
}

Claude Web/Mobile

Settings → Integrations → Add more
Enter URL: https://mcp.cardog.io/sse
Add your API key when prompted

Available Tools

Listings

Tool	Description
`search_listings`	Search vehicle inventory with filters for make, model, year, price, mileage

Market Analysis

Tool	Description
`get_vin_analysis`	Market analysis for a specific VIN
`overview`	Market statistics for make/model/year
`price_distribution`	Price histogram data
`get_odometer_analysis`	Mileage vs price correlation
`get_geographic_analysis`	Regional price variations
`get_market_trends`	Time series pricing data
`get_listing_market_position`	Individual listing analysis
`pulse`	Overall market health indicators

Vehicle Research

Tool	Description
`search_lineups`	Available models for a manufacturer
`get_model_year`	Trim levels and specs for a model year
`search_recalls`	Safety recalls (US & Canada)

Energy

Tool	Description
`search_electric_stations`	EV charging stations
`search_gas_stations`	Fuel stations with prices

Authentication

API key required. Provide via:

Method	Format
Query Parameter	`?api_key=YOUR_KEY`
Header	`Authorization: Bearer YOUR_KEY`
Header	`x-api-key: YOUR_KEY`

Get your API key: cardog.app/account/api

Examples

Find vehicles:

"Find Toyota RAV4s under $30,000 with less than 50,000 miles"

Market analysis:

"What's the market like for 2022 Honda Civics?"

VIN lookup:

"Check this VIN: 2T3P1RFV8NC123456"

Recall check:

"Are there any recalls on 2020-2023 Honda CR-Vs?"

Documentation

Support

Email: support@cardog.app
Status: status.cardog.ai

Install

Tools (5)

resolve_entityidentify_vehiclesearch_inventorymarket_quotecheck_recalls

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://mcp.cardog.io/mcp?api_key={api_key}

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.cardog.io/mcp?api_key={api_key}"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

Cardog MCP Server (app.cardog/mcp)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

resolve_entity

identify_vehicle

search_inventory

market_quote

check_recalls

Cardog MCP Server

Quick Start

Claude Code

Claude Desktop

Claude Web/Mobile

Available Tools

Listings

Market Analysis

Vehicle Research

Energy

Authentication

Examples

Documentation

Support

Install

Remote endpoint

Related servers