_ registry / mcp streamable-http · checked 5h ago

carfinity

https://carfinity.ai

Registry code: 2eab2ff088725b2e

api record

Carfinity ranks every new and used car at local dealers against its market. Use search_cars for what the shopper wants, get_car for why a car ranks where it does, market_summary for prices in a market. Quote prices as the dealer's advertised price, before tax, title and registration, and give the car's Carfinity link so the shopper can see the ranking. Never invent a car, a price or a shopper's contact details.

endpoint
https://carfinity.ai/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is carfinity live?
Yes — it answered the hub's last check (checked 5h ago). It answered 100% of checks over the last 30 days.
Is carfinity free to use?
Yes — the hub reached it with no key and no payment.
What tools does carfinity have?
7 tools: compare_cars, dealer_info, get_car, search_cars, market_summary, start_inquiry, list_markets.
Is carfinity safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
951ms

last good check

priced tools
0

of 7 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 7 tools
1 open 6 never probed 1 of 7 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • list_markets open 5h ago

    The markets Carfinity covers, with the number of cars in each.

    mcp-tool

    {
      "type": "object",
      "properties": {}
    }
    arguments 4 lines
  • compare_cars unknown 5h ago

    Compare 2 to 4 cars side by side on price, market price, percent under market, score, rank, mileage and dealer, and say which is the best deal.

    mcp-tool

    {
      "type": "object",
      "required": [
        "car_ids"
      ],
      "properties": {
        "car_ids": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 4,
          "minItems": 2,
          "description": "Car ids from search_cars."
        }
      }
    }
    arguments 17 lines
  • dealer_info unknown 5h ago

    A dealer's name, address, phone and website, how many new and used cars it has listed, and its best-ranked cars.

    mcp-tool

    {
      "type": "object",
      "required": [
        "dealer"
      ],
      "properties": {
        "dealer": {
          "type": "string",
          "description": "Dealer name or website domain."
        },
        "market": {
          "type": "string",
          "description": "Market slug, to narrow a common name."
        }
      }
    }
    arguments 16 lines
  • get_car unknown never probed

    Full details of one car: price against its market price, why it ranks where it does in plain sentences, mileage, color, drivetrain, photos count, the dealer and its phone, and the page to open. Use the id from search_cars.

    mcp-tool

    {
      "type": "object",
      "required": [
        "car_id"
      ],
      "properties": {
        "car_id": {
          "type": "string",
          "description": "The 12-character id of the car, or its Carfinity URL."
        }
      }
    }
    arguments 12 lines
  • search_cars unknown never probed

    Search new and used cars for sale at local dealers, in plain language. Every car comes back with its advertised price, its market price, how far under or over market it is, a deal label, a 0 to 100 score and its rank among comparable cars. Use a market name in the query or the market argument. Returns up to 10 cars per call, best deals first.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "page": {
          "type": "integer",
          "default": 1,
          "maximum": 10,
          "minimum": 1,
          "description": "Page of results, 10 cars each."
        },
        "sort": {
          "enum": [
            "best",
            "price",
            "price-desc",
            "miles",
            "newest"
          ],
          "type": "string",
          "default": "best",
          "description": "Order of results."
        },
        "query": {
          "type": "string",
          "description": "What the shopper wants, in their words. Examples: 'used SUV under $30k AWD', 'new Honda CR-V', 'certified Toyota under 40,000 miles', 'something cheap on gas for commuting'."
        },
        "market": {
          "type": "string",
          "description": "Market slug from list_markets, for example 'dallas-tx'. Optional if the query names the city."
        }
      }
    }
    arguments 35 lines
  • market_summary unknown never probed

    How many of a model (or kind of car) are for sale in a market, the median advertised price and mileage, the price range, and the share priced under market. Use it for questions like 'what does a used Camry cost in Dallas' or 'is now a good time'.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "query": {
          "type": "string",
          "description": "A model or kind of car, with new or used, for example 'used Toyota Camry', 'new Ford F-150', 'used SUV under $30k'."
        },
        "market": {
          "type": "string",
          "description": "Market slug from list_markets. Optional if the query names the city."
        }
      }
    }
    arguments 16 lines
  • start_inquiry unknown never probed

    Prepare a message to the dealer about one car on the shopper's behalf: availability, out-the-door price with fees, add-ons, history. Returns the exact message for the shopper to review. In this version the message is a preview and is not sent. Ask the shopper before calling this, and never invent their name or contact.

    mcp-tool

    {
      "type": "object",
      "required": [
        "car_id",
        "first_name",
        "contact"
      ],
      "properties": {
        "note": {
          "type": "string",
          "maxLength": 300,
          "description": "Anything else the shopper wants asked, in their words."
        },
        "car_id": {
          "type": "string",
          "description": "Car id from search_cars."
        },
        "contact": {
          "type": "string",
          "description": "Email or mobile number the shopper wants answers sent to, as they gave it."
        },
        "questions": {
          "type": "array",
          "items": {
            "enum": [
              "available",
              "otd",
              "addons",
              "history"
            ],
            "type": "string"
          },
          "description": "What to ask. Default: availability and out-the-door price."
        },
        "first_name": {
          "type": "string",
          "description": "The shopper's first name, as they gave it."
        }
      }
    }
    arguments 40 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 2eab2ff088725b2e.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/2eab2ff088725b2e/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/2eab2ff088725b2e/badge.svg)](https://brick.blue/agent/2eab2ff088725b2e?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.