Web & research

Lead screening

A lead plus your ICP criteria → a web-grounded qualification verdict with the evidence for and against.

POST /v1/screen$0.10/lead · 10 credits, charged only on success

Send this

{
  "lead": "brightco.io",
  "criteria": "B2B SaaS or agency, 20-200 people, US-based, runs client meetings at volume"
}

Every response carries usage — the credits burned and your remaining balance. A failed call never burns credits.

Try it live against your own key in the interactive reference; every account gets 500 free credits a month, no card.

Get this back

{
  "verdict": "qualified",
  "score": 0.86,
  "evidenceFor": [
    "~40 employees (LinkedIn)",
    "US HQ, Denver",
    "Agency model — client calls are the core motion"
  ],
  "evidenceAgainst": [
    "Recently switched tooling — may be locked in a contract"
  ],
  "profile": {
    "name": "BrightCo",
    "employees": "~40",
    "hq": "Denver, CO"
  },
  "usage": {
    "credits": 10,
    "balanceRemaining": 227
  }
}

Four ways in. Same $0.10/lead.

curl
curl https://api.kynth.studio/v1/screen \
  -H "Authorization: Bearer ksk_live_…" \
  -H "Content-Type: application/json" \
  -d '{"lead":"brightco.io","criteria":"B2B SaaS or agency, 20-200 people, US-based, runs client meetings at volume"}'
TypeScript
import { KynthCore } from "@kynth/api";

const kynth = new KynthCore({ apiKey: process.env.KYNTH_API_KEY! });
const result = await kynth.screen({
  "lead": "brightco.io",
  "criteria": "B2B SaaS or agency, 20-200 people, US-based, runs client meetings at volume"
});
Python
from kynth import Kynth

client = Kynth(api_key=os.environ["KYNTH_API_KEY"])
result = client.screen(
    lead="brightco.io",
    criteria="B2B SaaS or agency, 20-200 people, US-based, runs client meetings at volume",
)
MCP
// One-time setup in your MCP client (Claude, Cursor, …):
{ "mcpServers": { "kynth-core": {
    "command": "npx", "args": ["@kynth/api-mcp"],
    "env": { "KYNTH_API_KEY": "ksk_live_…" } } } }

// Then the agent just calls the kynth_screen tool.

More from web & research