canonical: https://jentic.com/apis/limitguard.ai/limitguard # Limitguard.ai The Limitguard API verifies the company behind a B2B sales lead against official business registers, with full coverage of the Dutch KVK and Belgian KBO registers, and cross-checks VAT numbers with VIES, mail servers, IBANs, and the OFAC, EU, and UN sanctions lists. Each lead check returns a verdict, a 0-100 lead score, and flags with one action per flag. Beyond leads it runs KYB checks, entity risk and reputation scores, deep checks for PEP ties, insolvency, and adverse media, sanctions screening by name, and agent wallet checks, and it can be paid per call with a prepaid key or an x402 payment in USDC. ## For AI agents Verify NL and BE sales leads, run KYB and entity trust checks, screen names against sanctions lists, and score entity risk and reputation. ## Scope Does not verify individual identity documents, enrich contact records with phone numbers, or send outreach. Use for company lead verification, KYB, and sanctions screening only. ## Capabilities - Verify a Dutch or Belgian sales lead against the KVK or KBO register and return a verdict, lead score, and flags - Run a KYB check across registry, sanctions, VAT/VIES, and domain from a registration number and country - Screen a name against the OFAC, EU, and UN sanctions lists - Score an entity's risk from 0 to 100 from its name and country - Check an entity for PEP ties, insolvency, and adverse media - Poll sanctions-list changes and hits on entities your key has checked, filtered by jurisdiction and severity - Check an agent wallet for sanctions, balance, and ERC-8004 identity ## Use cases ### Agent-run lead qualification through Jentic A sales or lead generation agent can check each inbound lead before it reaches the CRM: Limitguard confirms the company in the KVK or KBO register, validates the VAT number with VIES, checks the email domain's mail server, and screens the name for sanctions, then returns a verdict and a 0-100 lead score. Through Jentic the agent finds the lead verify operation by intent and loads its schema, so it qualifies leads without the developer wiring the call by hand. Example prompt: Search Jentic for 'verify a sales lead', then verify a lead with country NL, company_number 12345678, name 'Acme B.V.', and email 'info@acme.nl', and report the verdict, lead score, and any flags. ### KYB onboarding for business customers Before onboarding a business customer or supplier, a compliance step runs a KYB check from the entity_id, registration_number, and country, covering the registry, sanctions lists, VAT/VIES, and the domain, and returns a kyb_status and trust_score. A deep check adds PEP ties, insolvency, and adverse media, and a compliance report on the entity can be built and later re-fetched by its check_id. Example prompt: Run a KYB check with entity_id 'cust-001', registration_number '0123456789', and country BE, report the kyb_status and trust_score, then build a compliance report on the same entity by passing its entity_name and country. ### Ongoing sanctions monitoring Sanctions lists change daily. Limitguard's compliance alerts return changes to the OFAC, EU, and UN lists plus alerts when an entity or wallet your key already checked becomes listed, filterable by jurisdiction and severity, so a scheduled agent can poll for new hits. Example prompt: Poll compliance alerts with severity set to high and a limit of 50, and list any hits on entities this key has checked. ### Agent wallet trust checks For agent-to-agent commerce, the agent check screens a wallet against sanctions, reads its balance, and confirms its ERC-8004 identity, and a separate operation returns an ERC-8004 agent's USDC balance on Base. Example prompt: Check the wallet 0xabc123 with agent_id 'agent-42' and report its sanctions status and ERC-8004 identity. ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/v1/leads/verify` | Verify a sales lead | | POST | `/v1/kyb/check` | Run a KYB check | | POST | `/v1/entity/check` | Verify an entity across registries and risk layers | | POST | `/v1/sanctions/screen` | Screen a name against sanctions lists | | POST | `/v1/risk/score` | Score an entity's risk | | GET | `/v1/compliance/alerts` | Get sanctions changes and hits | | POST | `/v1/agent/check` | Check an agent wallet | | POST | `/v1/keys/create` | Create an API key | ## Key resources - **Leads** — Lead verification for NL and BE companies with verdict, lead score, and flags - **Entities** — Entity trust checks, deep checks, risk scores, reputation scores, and reputation history - **KYB** — Know-your-business checks across registry, sanctions, VAT/VIES, and domain - **Sanctions and compliance** — Name screening, sanctions alerts, compliance reports, and EU AI Act readiness - **Agent wallets** — Wallet checks and ERC-8004 agent USDC balance on Base - **Keys** — API key creation and prepaid balance top-ups ## AI readiness This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use. - **Score:** 46 / 100 - **Maturity:** Foundational - **Dimensions:** - Foundational Compliance: 74 / 100 - Developer Experience & Jentic Compatibility: 64 / 100 - AI-Readiness & Agent Experience: 22 / 100 - Agent Usability: 94 / 100 - Security: 50 / 100 - AI Discoverability: 79 / 100 - **View full report:** https://jentic.com/apis/limitguard.ai/limitguard/scorecard - **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/ - **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview ### Score it yourself Every API in the directory is allowlisted, so you can re-score it with no key required. - **Score your own API:** https://jentic.com/scorecard.md - **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md ```sh npx @jentic/api-scorecard-cli score ``` ## Why Jentic - **Setup:** Wiring Limitguard by hand means sending the X-API-Key header on the right operations, choosing between a prepaid key and x402 payment, and mapping each check's request body. Through Jentic you install once, import Limitguard from the API Directory, store the key once, and your agent calls it. - **Permission scoping:** Limitguard carries the company, name, and wallet in the request body, so rules bound which operations your agent may call, not which entity it checks. You choose the operations it may call, so ones that spend your balance, like the four key top-ups, are not included unless you add them. - **Credential handling:** Your Limitguard API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'verify a sales lead' or 'run a KYB check', and Jentic returns the matching Limitguard operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **ComplyAdvantage API** — AML screening and monitoring for customers - **OpenSanctions API** — Open sanctions and PEP entity data - **Kickbox Email Verification API** — Mailbox-level email verification ## FAQ ### What authentication does the Limitguard API use? Per its OpenAPI spec the Limitguard API takes an API key in the X-API-Key header, an lg_live_ key whose prepaid balance is debited per call. On the check and scoring operations the key is optional because an x402 payment can be sent instead, the balance top-up operations require the key, and key creation needs no authentication. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at request time. ### Is there a Limitguard MCP server? You don't need an MCP server to give your agent the Limitguard API. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent discovers the lead, KYB, and sanctions operations on demand instead of loading a set of tool definitions into its context. ### Can I verify a sales lead with the Limitguard API? Yes, for Dutch and Belgian leads. The lead verify operation requires a country and checks the KVK or KBO register for status, legal form, start date, main activity, staff, and registered address, then cross-checks whatever else you send: VAT number with VIES, the email's mail server and disposable domain, IBAN country and bank, and the name against the OFAC, EU, and UN sanctions lists. Inputs you leave out are not checked and never count against the lead. ### How much does the Limitguard API cost? The spec describes pay-per-call pricing: lead verify at $0.27 per lead, the agent check at $0.75 per wallet, and entity and risk checks at $0.88 to $1.05 fresh or $0.11 cached, with KYB at $1.50 fresh. A free sandbox key from the key creation operation with tier set to sandbox returns mock data for entity, risk, and KYB checks at no charge. ### What are the rate limits for the Limitguard API? The OpenAPI spec does not specify rate limits. Check the Limitguard documentation at https://docs.limitguard.ai for current limits. ### Can I limit what my agent is allowed to do with the Limitguard API? Yes. For example, write a rule that allows only the lead verify and sanctions screen operations, so the agent can qualify leads and screen names while the balance top-up operations, which spend money on your key, stay out of reach. Every call it makes is logged. ### How do I screen a company for sanctions with the Limitguard API through Jentic? Search Jentic for 'screen a name against sanctions lists', load the sanctions screen operation, and pass the name with an optional country. Jentic injects your X-API-Key at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.