IDEAKILLER// API
REST + MCP · $0.20/VERDICT · ZERO RETENTION GET API KEY →
EXAMPLE: focusflow CONDITIONAL 68EXAMPLE: dog-walking-marketplace NO-GO 34EXAMPLE: b2b-invoice-parser GO 81EXAMPLE: another-meditation-app NO-GO 29EXAMPLE: local-handyman-saas CONDITIONAL 62EXAMPLE: gym-class-reseller NO-GO 22EXAMPLE: niche-ecom-analytics GO 78EXAMPLE: focusflow CONDITIONAL 68EXAMPLE: dog-walking-marketplace NO-GO 34EXAMPLE: b2b-invoice-parser GO 81EXAMPLE: another-meditation-app NO-GO 29EXAMPLE: local-handyman-saas CONDITIONAL 62EXAMPLE: gym-class-reseller NO-GO 22EXAMPLE: niche-ecom-analytics GO 78
REST + MCP · BUILT FOR AI AGENTS

let agents kill
bad ideas
at scale

One REST or MCP call turns any idea into a GO / CONDITIONAL_GO / PIVOT / NO_GO verdict with scores and live-web evidence. $0.20 a call. And we never keep your idea — it is deleted right after the verdict is delivered.

◉ key in one POST · no sign-up ◉ $0.20 light · $0.50 full ◉ failed call = refunded
agent — POST /agent/v1/validations
● LIVE
$ agent → https://api.ideakiller.app/agent/v1
one POST. one verdict. zero storage.
API // COPY · PASTE · VALIDATE

one endpoint.
any agent.

Claude Code, Cursor, or your own agent loop — same key, same prices, same balance over REST and MCP.

validate.sh
# 1. Get a key — no email, no sign-up. Shown once.
curl -X POST https://api.ideakiller.app/agent/v1/keys

# 2. Validate an idea (light tier, $0.20, ~90 s).
curl -X POST "https://api.ideakiller.app/agent/v1/validations?wait=60" \
  -H "X-API-Key: ika_..." -H "Content-Type: application/json" \
  -d '{"idea_name": "AI tax filing for freelancers",
       "description": "Automates expense categorization, quarterly estimates and annual filing for US freelancers.",
       "price_point": 15, "business_model": "subscription",
       "tier": "light"}'

# 3. If the answer is 202, poll the poll_url.
curl "https://api.ideakiller.app/agent/v1/validations/{call_id}?wait=60" \
  -H "X-API-Key: ika_..."
AGENT FLOW // 04 CALLS

key → top-up →
validate → poll.

No dashboards, no OAuth dance. Four calls and your agent has a verdict with receipts.

01

key

/agent/v1/keys

One POST. No email, no sign-up, no dashboard. The key is shown once — your agent stores it.

02

top-up

/agent/v1/topups

Prepaid balance, minimum $20. The API returns a checkout_url — hand it to a human once, then run autonomously.

03

validate

/agent/v1/validations

POST the idea with ?wait=60. A light call lands in about 90 seconds and costs $0.20.

04

poll

/agent/v1/validations/{call_id}

Still running? You get a 202 and a poll_url. The result is delivered once, then deleted from our side.

RESPONSE // ANNOTATED

what your agent
gets back.

Structured JSON, not prose to parse. Verdict, conviction, six scores and evidence with live-web sources — ready for the next step in the agent loop.

{
"status": "COMPLETED", ← 202 + poll_url while still running
"tier": "light", ← light $0.20 · full $0.50
"cost_usd": 0.20,
"result": {
"verdict": {
"type": "CONDITIONAL_GO", ← GO · CONDITIONAL_GO · PIVOT · NO_GO — branch on it
"conviction": 55, ← 0–100 confidence in the verdict
"conditions_for_success": […],
"kill_criteria": [{ "trigger": …, "action": …, "deadline": … }] ← re-checks your agent can schedule
},
"scores": { ← all 0–100
"demand": 74, "competition": 42, ← competition: higher = more room
"problem_fit": 72, "economics": 58,
"risk": 62, "overall": 63 ← risk: higher = more danger
},
"demand": {…}, ← market size, search volume, sources
"competitors": {…}, ← competitors, gaps, sources
"unit_economics": {…}, ← LTV, CAC, churn, payback
"risks": {…}, ← failure modes with severity + mitigation
"pivot": null ← pivot ideas when the verdict is PIVOT (full tier)
}
}
DEPLOYED BY // AGENTS

agents that check
before they build.

$ startup_scouts

startup-scout agents

Your scout surfaces a hundred raw ideas a night. Make it prove them: only ideas with a verdict survive to your morning inbox.

$ vc_dealflow

vc deal-flow screening

Screen inbound decks at 3am. Verdict, conviction and six scores attached before a partner ever opens the PDF.

$ idea_generators

self-filtering generators

Generate → validate → kill. Your idea generator eats its own dog food and only shows users the ideas that pass.

$ founder_copilots

founder copilots

Before your copilot lets a founder burn the runway on a pivot, it checks the pivot. Two minutes of humility, on demand.

NEW // IDEA → DOMAIN

it passed.
now name it.

A GO verdict is worth nothing if the name hides what you sell. The domain finder builds names on words your buyers really search (real Bing volumes), checks them in the registry and returns 10 free ones with reasons. $0.20 a search — same key, same balance.

input one sentence
"Marketplace to rent camping gear from local people"
output free now
localcampgear.com"camping gear"
renttentgear.com"camping gear"
hikingcloset.com"hiking gear"
API PRICING // PER CALL

cheaper than
the prompt.

Your agent burns more than $0.20 thinking about whether to build. Pay per verdict, only when it is delivered — and the idea is deleted right after.

API · LIGHT
$0.20/call
~1.5 min
  • verdict + conviction
  • 5 scores + overall
  • live-web evidence per score
  • default tier
[ GET API KEY ]
API · FULL
$0.50/call
2–3 min
  • everything in light
  • deeper web research
  • competitor + risk detail
  • pivot ideas on PIVOT
[ GET API KEY ]
API · DOMAINS
$0.20/call
30–70 s
  • up to 10 free domains
  • built on real Bing search volumes
  • niche + competitor research
  • a reason for every name
[ GET API KEY ]
prepaid balance · min top-up $20failed calls are refunded to balancekey without sign-up — one POSTidea + report deleted after delivery10 calls/min · 5 running per keyllms.txt for your agent docs for agents: llms.txt
HUMANS // BROWSER PATH

prefer a form?
same engine, no code.

The web app runs the same analysis behind a three-minute flow. Free credits every month, no API key needed.

PRIVACY // ZERO RETENTION

we never keep
your ideas.

Other tools feed your idea into a training set or a trend report. Here, the idea and the report are deleted right after the verdict is delivered. Gone. Not "anonymized" — deleted.

✓ idea text and report are deleted right after the result is delivered
✓ a result that is never fetched is purged after 60 minutes
✓ we keep only the fact of the call: time, tier, price, duration
✓ ideas are never published and never used to train models
✓ for the analysis, the idea text goes to Google Gemini and the Tavily search API; domain search also sends short keywords to Bing
FAQ // AGENTS

questions,
answered.

Does my agent need an account to call the API?

No. One POST to /agent/v1/keys returns a key — no email, no sign-up. The key is shown once, so store it. The same key works for REST and MCP.

How does an agent pay for calls?

Every call is prepaid from a balance. POST /agent/v1/topups returns a checkout_url that a human pays once — minimum $20. After that the agent spends $0.20 per light call and $0.50 per full call on its own. There are no free calls.

What happens to my idea after the verdict?

It is deleted. Right after the result is delivered, the idea text and the report are wiped. A result that is never fetched is purged after 60 minutes. We keep only the fact of the call: time, tier, price, duration, and the error if it failed. Ideas are never published and never used to train models.

What if my agent sends garbage or an empty idea?

Nonsense or empty input is rejected up front, before any web search runs — and the call price is refunded. You never pay for a call that could not produce a real analysis.

What if a validation call fails midway?

The full call price goes back to your balance automatically. You only pay for delivered verdicts.

Is there an MCP server?

Yes: https://api.ideakiller.app/mcp (streamable HTTP, stateless). It exposes five tools — validate_idea, get_validation, find_domains, get_balance, create_topup — and uses the same key, prices and balance as REST. Works with Claude Code, Cursor and any MCP client.

Where are the machine-readable docs?

The full reference is at api.ideakiller.app/agent/v1/docs, and there is an llms.txt at api.ideakiller.app/llms.txt that any agent can read before its first call.

What are the rate limits?

Up to 10 validation calls per minute and 5 running validations per key. New keys are limited per network and per day.

stop funding
the wrong thing.

One call. Twenty cents. A verdict your agent can act on — and an idea we never keep.

IDEAKILLER.TERMINAL