_ registry / mcp streamable-http · checked 2h ago

com.mcpscores/vehicle-fault-codes

https://faultcode-diagnostic-mcp.bowling-anthony.workers.dev

Registry code: 1c8d87cceb73d89b

api record

You have a fault code, a VIN, or a car that may be recalled, and you must not guess what any of them mean. Tool calls are x402-paid in USDC on Base — send the base64 X-PAYMENT header on this POST /mcp request (or params._meta['x402/payment']). dtc_lookup costs $0.006; vehicle_recalls, vehicle_tsbs and vin_decode cost $0.005 each. An unpaid call returns a PaymentRequired result carrying the x402 accepts challenge and settles nothing; initialize, ping and tools/list are free, and a call missing a required argument is refused before payment is ever requested. We never guess a code meaning: an…

endpoint
https://faultcode-diagnostic-mcp.bowling-anthony.workers.dev/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 com.mcpscores/vehicle-fault-codes live?
Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is com.mcpscores/vehicle-fault-codes free to use?
No — it charges per call, from 0.006 USDC, quoted in its own 402 answers.
What tools does com.mcpscores/vehicle-fault-codes have?
4 tools: vehicle_tsbs, vehicle_recalls, vin_decode, dtc_lookup.
Is com.mcpscores/vehicle-fault-codes 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
99.7%

90 days 99.4%· all time 99.4%

latency
121ms

last good check

priced tools
1

of 4 tools

_ answered our checks, 90 days 648 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
used for
  • look up a vehicle fault code
  • check vehicle recalls
  • get technical service bulletins
  • decode a vin
takes → gives
text → data
tools
4 reads
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts, and USDC settlements on base into the address this listing's priced doors name, read off the chain. Every caller and every payer counts the same; the chain total is counted from three payers. The address also stands behind 12 other origins: the chain figures are the gateway's, not this listing's alone. How it is counted.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

payers on base
15

distinct

settlements
39

last 2026-11-05

received on chain
0.228 USDC

shared-payto

_ what it can do 4 tools
1 paid 3 never probed 1 of 4 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.

  • dtc_lookup reads 0.006 USDC paid 13h ago

    Look up what a vehicle fault code (OBD-II diagnostic trouble code) means. Returns a reworded definition compiled from open/public sources (with the source and licence per row) plus which makes define the code specifically. Pass 'make' for the make-specific meaning instead of the generic SAE one — the same code can mean different things on different brands. Use this when a scan tool reported a code like P0301, B1318 or U0100; we never guess a meaning (unknown codes return not_found). Descriptions are compilations, not manufacturer verbatim strings, and severity is not guaranteed. Costs $0.006 USDC per call via x402 on Base.

    mcp-tool

    {
      "type": "object",
      "required": [
        "code"
      ],
      "properties": {
        "code": {
          "type": "string",
          "examples": [
            "P0301"
          ],
          "description": "The fault code exactly as reported, e.g. 'P0301', 'B1318', 'C1201', 'U0100'."
        },
        "make": {
          "type": "string",
          "examples": [
            "BMW"
          ],
          "description": "Vehicle make for the manufacturer-specific definition, e.g. 'BMW', 'Ford', 'Toyota'. Optional; omit for the generic SAE meaning."
        }
      },
      "additionalProperties": false
    }
    arguments 23 lines
  • vehicle_tsbs reads unknown never probed

    NHTSA Technical Service Bulletins (manufacturer repair guidance for known defects that are not safety recalls). Returns bulletin id, summary, and the fault codes each bulletin names (max 50). Query by make/model/year, or by fault code to find bulletins that address that specific code. Use this after dtc_lookup when you want the manufacturer's documented fix. A zero count means nothing matched the ingested subset. Costs $0.005 USDC per call via x402 on Base.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "code": {
          "type": "string",
          "examples": [
            "P0301"
          ],
          "description": "Fault code to match against the bulletin's listed codes, e.g. 'P0301'. Optional."
        },
        "make": {
          "type": "string",
          "examples": [
            "TOYOTA"
          ],
          "description": "Consumer make name, e.g. 'TOYOTA'. Required unless 'code' is given."
        },
        "year": {
          "type": "string",
          "examples": [
            "2019"
          ],
          "description": "Four-digit model year, e.g. '2019'. Optional."
        },
        "model": {
          "type": "string",
          "examples": [
            "CAMRY"
          ],
          "description": "Model name, e.g. 'CAMRY'. Optional."
        }
      },
      "additionalProperties": false
    }
    arguments 34 lines
  • vehicle_recalls reads unknown never probed

    Official NHTSA safety recalls for a vehicle. Returns campaign id, affected component, the safety consequence, and the free remedy, newest first (max 50). Query by make (optionally model and year) or by a known campaign id. Use this before buying a used vehicle or when a customer asks whether their car has open recalls. A zero count means nothing matched the ingested NHTSA subset — it does not prove the vehicle is recall-free. Costs $0.005 USDC per call via x402 on Base.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "make": {
          "type": "string",
          "examples": [
            "FORD"
          ],
          "description": "Consumer make name, e.g. 'FORD', 'TOYOTA'. Required unless 'campaign' is given."
        },
        "year": {
          "type": "string",
          "examples": [
            "2018"
          ],
          "description": "Four-digit model year, e.g. '2018'. Optional."
        },
        "model": {
          "type": "string",
          "examples": [
            "F-150"
          ],
          "description": "Model name, e.g. 'F-150', 'CAMRY'. Optional."
        },
        "campaign": {
          "type": "string",
          "examples": [
            "21V123000"
          ],
          "description": "NHTSA campaign id to fetch directly, e.g. '21V123000'. Optional."
        }
      },
      "additionalProperties": false
    }
    arguments 34 lines
  • vin_decode reads unknown never probed

    Decode a Vehicle Identification Number into make, model, model year, body class, engine and plant country using NHTSA's public vPIC database. Use this when you have a VIN and need the exact vehicle before looking up recalls or bulletins. Costs $0.005 USDC per call via x402 on Base.

    mcp-tool

    {
      "type": "object",
      "required": [
        "vin"
      ],
      "properties": {
        "vin": {
          "type": "string",
          "examples": [
            "1HGCM82633A004352"
          ],
          "maxLength": 17,
          "minLength": 11,
          "description": "The VIN, 11-17 characters, e.g. '1HGCM82633A004352'."
        }
      },
      "additionalProperties": false
    }
    arguments 18 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 1c8d87cceb73d89b.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/1c8d87cceb73d89b/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/1c8d87cceb73d89b/badge.svg)](https://brick.blue/agent/1c8d87cceb73d89b?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
80%

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.