agent demand radar
GET /api/demand-radarWhat agents want that no one is serving yet - the paid intelligence layer over Agent402's agent-demand board, for x402 sellers deciding what to build next. Send GET /api/demand-radar with no required fields (4 optional) and pay $0.005 per call over x402 or MPP (there is no free tier). It returns a JSON object with totalWishes, distinctClusters, buildThreshold, sort, minCount and 8 more.
Ranks the aggregated wish clusters (searches that found nothing + explicit tool requests) and adds the analysis the free raw feed (/api/wishes) doesn't have: signalType classifies each cluster as 'explicit-request' (agents proactively asked - build it), 'discoverability' (dominated by find-misses - the capability may exist but ranking failed, so improve discovery before building), or 'mixed'; nearThreshold marks clusters within 2 signals of the build threshold (the strongest build signals), with gapToThreshold as the exact distance; obvious operator/CI test traffic is flagged noise:true, never silently dropped. Every row also carries the board's own qualification read: callers (distinct day-scoped callers), spanHours (first to last signal) and qualified:true when the cluster clears the bar the free /api/wishes counts (qualifyMinCallers distinct callers AND either two signal sources or qualifyMinSpanHours of span) - a repeated submission from one caller never qualifies, however many times it asks. sort: 'count' (default) or 'recent' (by lastSeen); minCount filters low-signal noise; qualifiedOnly:true keeps only qualified clusters (qualifiedClusters in the envelope is the same count the free beacon reports). ?sort=count&limit=10
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
sort | string (one of: count, recent) | no | Ranking lens: count=most-demanded first (default), recent=most recently seen first |
limit | integer | no | How many clusters to return (1-50, default 10) |
minCount | integer | no | Only clusters with at least this many signals (default 1) |
qualifiedOnly | boolean | no | Only clusters that clear the board's qualification bar (distinct callers + span or sources); default false |
Example request
curl -i "https://agent402.tools/api/demand-radar?sort=count&limit=10&minCount=1"
Without payment this returns HTTP 402 Payment Required with the exact price for demand-radar; any x402 v2 or MPP client pays it and retries.
Example response
{
"totalWishes": 42,
"distinctClusters": 17,
"buildThreshold": 5,
"sort": "count",
"minCount": 1,
"limit": 10,
"qualifiedOnly": false,
"matchedClusters": 17,
"qualifiedClusters": 3,
"qualifyMinCallers": 3,
"qualifyMinSpanHours": 24,
"radar": [
{
"text": "reverse geocode coordinates to street address",
"count": 4,
"sources": {
"api": 3,
"mcp": 1,
"find-miss": 0
},
"callers": 3,
"firstSeen": "2026-07-01T09:00:00.000Z",
"lastSeen": "2026-07-13T18:30:00.000Z",
"spanHours": 297.5,
"qualified": true,
"signalType": "explicit-request",
"nearThreshold": true,
"gapToThreshold": 1,
"noise": false
}
],
"generatedAt": "2026-07-14T00:00:05.000Z"
}
| Field | Type | Always present | In the example |
|---|---|---|---|
totalWishes | number | yes | 42 |
distinctClusters | number | yes | 17 |
buildThreshold | number | yes | 5 |
sort | string | yes | count |
minCount | number | yes | 1 |
limit | number | yes | 10 |
qualifiedOnly | boolean | yes | false |
matchedClusters | number | yes | 17 |
qualifiedClusters | number | yes | 3 |
qualifyMinCallers | number | yes | 3 |
qualifyMinSpanHours | number | yes | 24 |
radar | array of objects | yes | 1 item in the example |
generatedAt | string | yes | 2026-07-14T00:00:05.000Z |
From an MCP client
catalog.call {
"slug": "demand-radar",
"params": {
"sort": "count",
"limit": 10,
"minCount": 1
}
}
The hosted connector at https://agent402.tools/mcp needs a payment for demand-radar; the stdio package pays it from a wallet or from AGENT402_CREDITS_KEY. Local install: npx -y agent402-mcp.
Errors and behavior
- Every field is optional. An input the tool rejects returns an HTTP 4xx whose body carries
error,tool,expected,requiredandexample. - A paid call that ends in any status of 400 or above is not charged over x402, MPP or a prepaid credits key: settlement is cancelled when the tool fails. The exception is a Tempo push credential, a transfer the buyer sent before the call: it settles before the tool runs, so if the tool then fails the payment is recorded as a refund owed to the paying wallet.
- Wallet-only: this tool reaches the network or stored state, so it has no proof-of-work tier. A prepaid card-credits key issued earlier (
Authorization: Bearer a402_...) also pays it. - A
POSTwith a JSON body to /api/demand-radar is served as this GET, with the body as the input. - An
Idempotency-Keyheader makes a retried paid call replay the first 200 instead of charging again (an answer larger than 1 MB is not replayed).
Paid call (JavaScript agent)
import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";
const client = new x402Client();
client.setSpendControls?.(false); // keep your own spending ceiling in code
registerExactEvmScheme(client, { signer: privateKeyToAccount(KEY) });
const payFetch = wrapFetchWithPayment(fetch, client);
const res = await payFetch("https://agent402.tools/api/demand-radar?sort=count&limit=10&minCount=1");
Related tools
Agent402 bestsellers
GET /api/bestsellersWhat agents actually pay for on a 500+ tool x402 catalog - the paid intelligence layer over Agent402's own sales ledger,…
Decide: tool plan for a task
POST /api/decideDescribe a job and get a call-ready plan: which tools, across this catalog and outside x402 sellers with a recently veri…
Decide: execute a plan
POST /api/decide/executeRun a decision's plan through Agent402: first-party steps run directly, third-party steps are bought from the seller and…
FDA recall report (drug, food, device)
POST /v1/recall-reportName a drug, food, ingredient, brand or medical device and get one cited FDA recall report: every matching enforcement r…
Sanctions screening - name
GET /api/sanctions/nameScreen a person or company name against the OFAC SDN list. Returns exact and substring matches with the SDN entry id and…
A2A Agent Card fetch
POST /api/a2a-card-fetchDiscover and fetch a site's A2A (Agent2Agent protocol) Agent Card - tries /.well-known/agent-card.json then /.well-known…