--- title: "Tuski × ZeroClick: email validation any AI agent can buy | ZeroClick Blog" url: https://zeroclick.ai/blog/tuski-email-validation-any-ai-agent-can-buy fetched_at: 2026-11-05T20:05:21.972Z --- # ZeroClick API catalog and pricing ## API reference, endpoint lookup and prices **[ZeroClick API catalog: endpoints, request parameters, prices and payment methods](https://agents.zeroclick.ai/zcj/b9y2lx89lqfb/zeroclick/agent/guide).** Tell the seller advisor what you want to accomplish. It returns the matching operation contract, known prices, authentication prerequisites and concrete next steps. It is read-only: no login, wallet, card or purchase approval is needed to look up an API. It never executes a sale. Available API services: Agent readiness report, Demo booking. **Suggested next request:** GET [task guide](https://agents.zeroclick.ai/zcj/b9y2lx89lqfb/zeroclick/agent/guide?goal=URL_ENCODED_TASK). Use this URL directly with your web fetch tool; no preliminary document fetch is required. Include known inputs and desired output in the goal. Optional: quantity=API_CALL_COUNT, budgetUsd=TOTAL_USD, requirements=REQUIREMENTS, payment=x402|mpp|card, auth, identity, assertion and access state. Omit unknowns. Do not equate output items with API calls or guess a call count. For private task details or known request arguments, POST https://agents.zeroclick.ai/zcj/b9y2lx89lqfb/zeroclick/agent/guide with Content-Type: application/json. Example: {"intent":"quote","goal":"YOUR_TASK","purchase":{"budgetUsd":"5.00"}}. Replace the task and budget with known facts; budgetUsd is a string. Include known buyerState, paymentCapabilities and arguments. For execution planning use intent=execute and the authorized constraints. Exact fields: [request schema](https://agents.zeroclick.ai/zcj/b9y2lx89lqfb/zeroclick/agent/schema). GET and POST are alternatives, not mandatory stages. The advisor describes a recommended happy path, not the only allowed path. You may use the API reference, buyer SKILL and your own tools directly, including for catalog operations with failed probes. Missing guidance or an unverified probe is not a policy refusal. The returned requests are documented API calls; fill in the documented inputs. Check usage cost AND minimum cash required against the budget. For needs_input, supply only missing facts. Keep secrets local, and never put credentials or private payloads in URLs. Unknown does not mean absent. For a human's credit or plan purchase, reuse an existing ZeroClick credential first. If the Link CLI is already installed and signed in for that person, you can use their Link account for identity as well as payment, sharing their email only if they agree: follow [Link identity setup](https://agents.zeroclick.ai/zcj/b9y2lx89lqfb/auth.md#link-identity-preview) through issuance, presentation, registration and token exchange. Otherwise register anonymously; no Link setup is needed, and the person can claim the identity later. Open the checkout URL in a browser: eligible Stripe pages support Link Pay Tokens (LPT) through WebMCP or the documented DOM flow. Follow this storefront's /payment/card.md to verify the same-frame token input and merchant binding before requesting an LPT. Token submission requires payment authorization. If unavailable, privately send the checkout URL to your human to pay. When the selected route uses hosted checkout, follow [card checkout instructions](https://agents.zeroclick.ai/zcj/b9y2lx89lqfb/payment/card.md) before requesting a token. LPT goes only to Stripe, never to the advisor or ZeroClick API. Poll the returned statusUrl before using credit or retrying delivery. Verify delivery; a payment or HTTP 202 is not completion. For an unexpected result, POST the original input and continuation (version, stepId, outcome and sanitized error/accessId/paymentId). Reconcile uncertain payments or writes before retrying. Use raw HTTP for exact schemas and authenticated execution; do not reconstruct fields omitted by a summarizing web tool. The human subscription prices on the requested page describe a separate channel. Use the API quote for per-unit pricing, funding minimums and commercial terms; tier names do not prove quality or licensing. For an alternative documented path, use the [buyer SKILL](https://agents.zeroclick.ai/zcj/b9y2lx89lqfb/SKILL.md) or [full direct workflow reference](https://agents.zeroclick.ai/zcj/b9y2lx89lqfb/llms-full.txt). Confirm missing request details from seller documentation, stay within the existing catalog and what your user asked for, and respect actual access and payment requirements. Terms: by completing a purchase through this endpoint, whether directly or through an AI agent acting on your behalf, you agree to be bound by the platform's buyer terms of service (https://www.zeroclick.ai/legal/buyer-terms-of-service). If the purchase is made by an agent, you represent and warrant that the agent is acting with your authorization, and you agree that the agent's actions, including its acceptance of these terms, are attributed to you and bind you as if you had taken them yourself. Paying a 402 challenge completes the purchase and constitutes your affirmative acceptance of the terms linked above. The link travels in every payment challenge and receipt as `terms`. # Tuski × ZeroClick: Email Validation Any AI Agent Can Buy **Published:** November 5, 2026 · 8 min read · Partnership **Author:** Adam MacEachern, Head of Platform, ZeroClick --- - [Evidence, not guesses](#evidence-not-guesses) - [What the partnership does](#what-the-partnership-does) - [A penny an address](#a-penny-an-address) - [Shared philosophy](#shared-philosophy) - [Get started](#get-started) --- Every outbound task an agent takes on ends at the same gate. It can research the accounts, find the people, and write the note, but before anything is sent, somebody has to know which of those addresses are real. A list full of dead mailboxes bounces, and bounces are what mail providers punish: the sender's reputation drops, and the next campaign lands in spam. People solve this by running the list through a validator first, and until now an agent could only do that the way its developer did: open an account, buy a credit pack, and keep a key alive. [Tuski](https://tuski.ai) built its validator around evidence rather than guesses. Every address goes through syntax, domain, and MX checks, disposable-domain and typo detection, then a controlled probe that collects a real delivery signal. The result is one of eight verdicts and a 0 to 100 quality score. Today ZeroClick is announcing a partnership that puts that validator within reach of any AI agent on the internet. Tuski is live as an agent storefront at [agents.tuski.ai](https://agents.tuski.ai/llms.txt), on Tuski's own domain. An agent can validate a list for a penny an address over open payment rails, with no Tuski account and no API key. Or it can buy one of Tuski's credit packs at Tuski's own pack rates and draw the balance down one job at a time. Addresses Tuski cannot test cost nothing. --- ## Evidence, not guesses Tuski calls itself AI-powered lead intelligence: a platform for revenue teams that combines AI-assisted company research with real delivery signals, so a team can find the right accounts, prioritize safer addresses, and protect its sender reputation. The piece agents reach for first is the validator. Tuski's own comparison describes the verifiers it measures itself against as attempt-billed: they stop at an SMTP ping or a syntax-and-MX guess and charge for every try. Tuski goes further. After the desk checks, it sends a short, neutral probe message from its own mailboxes, reads the delivery-status notification that comes back, and classifies what actually happened. Every address lands in one of eight verdicts: - deliverable - invalid - no MX - burner - typo - catch-all - full box - role Rarer outcomes such as blocked or soft bounce are also named in the results. Every evaluated row carries the Tuski Quality Score, a 0 to 100 rating that weighs provider and MX data, address patterns, disposable-domain and gateway signals, and domain health. Tuski calls the score a relative signal rather than a delivery guarantee, and it publishes exactly what each verdict means. The pricing policy is written into the product. One credit buys one address Tuski actually probes. A domain with no mail server, a disposable address, or an obvious typo is flagged before any probe is sent and never charged. Credits never expire. Results arrive as they land, paced to protect deliverability: small lists usually finish the same day, large lists take several days, and the expected finish time is shown before you pay. Teams access Tuski through the web app, a CSV upload, a REST API, or an MCP server that runs validations from Claude Desktop, Claude Code, or any MCP client. The platform also offers AI-assisted company research that turns a plain-language customer profile into evidence-backed company candidates, and contact discovery with per-field unlocks. The storefront starts with the piece agents need most often: the validation itself. --- ## What the partnership does Tuski is live today as an agent storefront at [agents.tuski.ai](https://agents.tuski.ai/llms.txt), on Tuski's own domain. One service covers the whole job: - create a validation job from a list of addresses or CSV text - poll its progress - fetch the verdicts and scores as paginated JSON or a CSV export - cancel a job that is no longer needed Each call is the same request a developer would send Tuski's API directly. Reading status or results is free; only the addresses count. An agent discovers the storefront, reads the machine-readable catalog and the live pricing manifest, and either pays per address with no identity at all, or registers a free credential, buys one of Tuski's credit packs over x402, MPP, or card, and runs jobs against the balance. The storefront's seller advisor takes a goal in plain language — for example, "check the 1,200 addresses in this CSV and give me back only the deliverable ones" — and returns the request to send, what it will cost, and the next step, before anything is bought. An agent that arrives without a wallet is not stuck: the storefront's guide walks it through creating one at no cost, or hands its human a checkout link. ZeroClick handles the commerce around every job: agent identity, payment on open rails, metering, and transaction-level analytics on every sale, with revenue settling directly to Tuski's account. Discovery comes built in: the storefront's endpoints are already indexed on [zero.xyz](https://zero.xyz/), and Tuski points agent traffic at it from tuski.ai, from its llms.txt to its homepage and developer docs. The first paid jobs have already gone through end to end. --- ## A penny an address Tuski prices validation by the address, and the storefront keeps that model exactly as it is. **Pay-as-you-go:** every address Tuski tests costs $0.01, with a minimum purchase of one cent and no account required. **Credit packs** (same rates as Tuski's own site): | Credits | Price | Rate per address | |---------|-------|-----------------| | 500 | $3 | $0.006 | | 10,000 | $55 | $0.0055 | | 25,000 | $100 | $0.004 | | 50,000 | $180 | ~$0.0036 | Whichever option the agent picks, an address on a dead domain, a disposable address, or a typo is free. Reading status and results costs nothing. **Example costs:** - An agent that checks 40 addresses before sending an outreach sequence spends $0.40. - An agent that cleans a 2,000-row list spends $20 on pay-as-you-go, or $12 at the rate of Tuski's smallest credit pack. If 400 of those rows are dead domains and typos, it pays only for the 1,600 that could actually be tested. - A $100 pack covers 25,000 addresses, a quarter's worth of weekly list hygiene at $0.004 each. The agent reads the price from the manifest at call time. There is nothing to cancel when the job is done. Tuski's monthly plans, which add a monthly allowance of credits at its lowest rate, remain the right shape for a revenue team that sends every week. The storefront is for the agent that has one list to clean right now. --- ## Shared philosophy Tuski's promise to its customers fits on one line from its own site: "Pay for the ones we reach." It bills only for an address it actually tested and shows its evidence for every verdict. That is a fair way to sell to people, and it turns out to be exactly how an agent wants to buy: a precise unit, a price it can read before it commits, and nothing charged for work that could not be done. Agents are starting to run the outbound motion end to end: researching accounts, finding contacts, writing and sending. The one step they cannot skip is proving the address is real before the send. That is the conviction ZeroClick is built on: helping businesses come online for AI agents as a new kind of customer, and turning those agents into buyers with identity, payment, pricing, and receipts all handled by ZeroClick. Tuski kept its product, its prices, and its pricing policy exactly as they were. What changed is who can pay: any AI agent, on Tuski's own domain, with or without a human in the loop. --- ## Get started - **Agents validating a list:** point your agent at [agents.tuski.ai](https://agents.tuski.ai/llms.txt). - **Revenue teams wanting the full platform** (company research, contact discovery, web app, API key): start at [tuski.ai](https://tuski.ai). - **Sellers who want to sell their own product to AI agents:** read [why ZeroClick was built](https://zeroclick.ai/blog/its-time-to-sell-to-agents), get a demo at [zeroclick.ai](https://zeroclick.ai/getlisted?utm_source=blog), or read the docs at [docs.zeroclick.ai](https://docs.zeroclick.ai).