Brand Name Clearance — is this name safe to use?

One call answers what every founder and AI agent asks before committing to a name: can I actually use it?

Send a name + one-line product description. Get one structured verdict from official public sources:

• Trademark knockout: USPTO + TMview (EUIPO's aggregation of 70+ IP offices) — live/pending marks only
• Phonetic & fuzzy matching — catches Kwik/Quick, Lyft/Lift conflicts, not just exact hits
• Nice-class inference from your description
• Domains via RDAP (com, io, co, ai, app, dev)
• Handles (GitHub, X, Instagram) — best-effort, labeled
• One grade: CLEAR / CAUTION / HIGH_RISK / UNKNOWN
• Alternatives that clear the same knockout

Pricing

$0.10 per completed verdict ($100 / 1,000). That's the whole model: no subscription, no minimum, no tiers.

What is never charged: runs where a trademark source failed, errors, and partial results. You pay for verdicts, not apologies. For comparison, a single manual knockout search — USPTO, then TMview, then domains, then handles — takes a person about an hour.

Agent-first (MCP)

Call it mid-conversation from Claude, ChatGPT, Cursor, n8n, Make, or any MCP client. Deterministic JSON out.

Listed in the official MCP registry as io.github.sreichsbb-stack/reich-tools. Add to any MCP client:

{
  "mcpServers": {
    "reich-tools": {
      "url": "https://mcp.apify.com?tools=shane_reich/name-clearance-verdict,shane_reich/stock-edge-signals"
    }
  }
}

Example

{"name": "Zephyrion", "description": "AI fitness app"} → HIGH_RISK — live mark 'ZEPHYRION' — identical

Real result: "Zephyrion" looks free but carries a registered EU mark (class 9) and a live US filing (class 20). Exactly the collision this catches before it costs you.

Honesty

• A grade is never CLEAR if a trademark source failed — partial searches say so, loudly.
• Handle checks are best-effort and labeled.
• This is a knockout search, not legal advice. Identical names can coexist across unrelated classes; near misses can be fatal in related ones. Final calls belong with IP counsel.

Watch mode — keep watching a name you cleared

A verdict tells you the name is safe today. Watch mode tells you when that changes.

Run the Actor with mode: "watch" and it re-runs the same trademark screen (USPTO + TMview, 70+ offices) for that name and alerts ONLY on new confusable filings since your last watch run:

{ "mode": "watch", "name": "Zephyrion", "description": "AI fitness app" }

• First run: BASELINE_CREATED — snapshots every confusable mark on record.
• Later runs: NO_NEW_FILINGS, or NEW_FILINGS_FOUND with the new marks (office, application number, status, Nice classes, and oppositionPeriodEnd when the registry provides it — the date that matters: oppose early instead of litigating later).
• If a trademark source fails mid-check: WATCH_INCONCLUSIVE — you are not charged and the baseline is untouched. A watch that silently misses filings during an outage is worse than no watch; this one refuses to.

Pricing: one watch-check event ($0.04) per completed watch run. Errors and inconclusive checks are never charged.

Set-and-forget in 2 minutes (no code):

1. Open the Actor, set the watch input above, and Save as a task.
2. Schedules → create a schedule (weekly suits most marks) → point it at the task.
3. On the task, add an integration (email, Slack, or webhook) on finished runs — each run's dataset record carries watchStatus and newFilings.

Watching several names? One task per name — each keeps its own baseline. AI agents: call the same input on your own cadence via MCP or x402; watch state persists in your account between runs.

Agentic payments (x402)

AI agents can run this Actor autonomously — no Apify account or API key required. Pay per verdict in USDC via the x402 protocol using a prepaid token from https://agi.apify.com/protocols/x402/prepaid-tokens.

Two events: verdict at $0.10 per clearance and watch-check at $0.04 per watch run. Errors and UNKNOWN / inconclusive results are never charged.

curl -s -X POST \
  -H "Authorization: Bearer $PREPAID_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"name": "Zephyrion", "description": "AI fitness app", "check_alternatives": true}' \
  "https://api.apify.com/v2/actors/shane_reich~name-clearance-verdict/run-sync-get-dataset-items"

Why

I built this after watching people fall in love with names that were already taken — and only finding out after the logo, the domain hunt, and the printing. Five seconds of checking beats months of rebranding. It's maintained, honest about its limits, and if it breaks I fix it. Tell me which office or TLD you need next.

---

Part of the Reich "tools that tell you the truth" line — see also Stock Edge Signals.