Pay-per-call UK MOT history, reliability analytics and identifier utilities. x402 USDC on Base.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Pay-per-call UK data and utility API, gated by x402 micropayments on Base mainnet. No API keys, no accounts, no subscriptions β send a signed USDC payment with your HTTP request and get an answer back in the same response cycle.
https://api.databroker.mossforge.deveip155:8453)exact scheme/v1/discover is free and returns every enabled dataset with its current price, description,
and provenance (kind, implemented standard, deterministic, data_source). Prices are
configured server-side and can change β always trust the live 402 challenge over anything
written in this README.
Requesting any paid route without payment returns HTTP 402 with the exact amount, recipient,
and network in a PAYMENT-REQUIRED header. Sign an EIP-3009 USDC transfer authorization, retry
with a PAYMENT-SIGNATURE header, and the API verifies, settles on-chain, and returns the data
with a PAYMENT-RESPONSE receipt. A 402 means no funds have moved β you only pay on a 200.
x402 client libraries: @x402/fetch
(TypeScript), x402 (Python),
x402-go (Go).
@mossforge/databroker-mcp gives any MCP client (Claude Desktop, Claude Code, Cursor)
pay-per-call access to everything below, with x402 payment handled for it. No build step:
Or for Claude Code:
Payment is never automatic. databroker_fetch and databroker_batch_create return a
price quote first and spend nothing until called again with confirm: true
enforced in the server, not left to the model's judgement. Every paid call is additionally
capped by DATABROKER_MAX_USDC; anything priced above the cap is declined before payment.
See mcp-server/ for signer options (self-custodied key or Coinbase CDP)
and security notes.
Three OpenClaw skills in skills/, scoped by tier - mossforge-mot-history
(single vehicle), mossforge-mot-analytics (fleet statistics), mossforge-data-utilities
(24 identifier/geo/reference endpoints).
Worked examples in examples/ for Python and TypeScript, both as a plain
fetch and as an agent tool definition.
All paid routes follow the same shape: GET /v1/{dataset_id}/{key}. Keys are URL-decoded
server-side, so percent-encode anything containing /, spaces, or +
(e.g. 205/55R16 91V β /v1/util-tyre-size/205%2F55R16%2091V).
| Route | Description |
|---|---|
GET /v1/health | Uptime check |
GET /v1/discover | All enabled datasets, current prices, provenance |
GET /v1/{dataset}/{key}/meta | Cache freshness for cached datasets; kind/standard/determinism info for utilities. Never returns the data payload |
Stored datasets backed by ingestion pipelines, with full freshness semantics (ttl_seconds,
stale, free /meta checks).
| Dataset | Route | Price | Description |
|---|---|---|---|
| DVSA MOT history | GET /v1/dvsa-mot/{registration} | $0.005 | Full MOT test history for a UK vehicle β vehicle details, pass/fail summary, mileage, individual test records with defects. Cached 30 days; first-ever lookup for a plate triggers a live fetch (2-4 s) |
| DVSA MOT analytics | GET /v1/dvsa-mot-analytics/{key} | $0.02 | Aggregated MOT statistics by vehicle segment β pass rates, top defects, mileage percentiles, clocking rates, fuel mix, colour distribution. Refreshed daily from the full DVSA bulk dataset |
Analytics keys are colon-delimited and family-specific:
| Family | Key format | Example | Returns |
|---|---|---|---|
| reliability | reliability:<make> | reliability:ford | Pass rates by age and mileage band, first-time pass rate, dangerous defect rate |
| mileage | mileage:<make>:<band_or_year> | mileage:ford:5-8yr | Average annual mileage, percentile distribution, odometer clocking rate |
| parc | parc:<make>:<fuel>:<band_or_year> | parc:ford:diesel:5-8yr | Fleet population counts and recent testing activity |
| fuelmix | fuelmix:<year> | fuelmix:2019 | Fuel type distribution for a registration year |
| colour | colour:<make>:<year> | colour:ford:2019 | Top colours for a make/year |
| temporal | temporal | temporal | UK-wide test volume, pass rate, expiry density by month |
Age bands: 0-3yr, 3-5yr, 5-8yr, 8-12yr, 12yr+. Fuels: petrol, diesel, electric,
hybrid, other. Derived rates are suppressed to null (with lowSample: true) when the
underlying sample is below minN, so small segments never yield misleadingly precise numbers.
Pure deterministic functions exposed as paid endpoints. The same key always returns the same
answer, forever β responses carry deterministic: true, so cache them client-side indefinitely.
Every response names the standard it implements. Malformed keys are rejected with a free 400
before payment; for validators, valid: false is a legitimate paid answer β you pay for the
verdict, not for the verdict being yes.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/databroker)<a href="https://allmcps.com/mcp/databroker"><img src="https://allmcps.com/api/badge/databroker?style=directory" alt="Databroker on AllMCPs" /></a>