One store for your agents.
From checks to missions.

Quick Bierus website audit (audit-live engine, 6 steps): reads the site, asks AI assistants (Google AI Mode/Overview, ChatGPT, an LLM), checks online reputation, Lighthouse mobile speed and security headers, then writes findings with evidence and a PDF report (EN/FR). Async: job_id + free result_url; typically about 2 min of work (66-190 s measured) plus queue. Pay on delivery: settled only when the report is delivered; a failed or blocked audit is never charged.

Full Bierus v2 website audit: ~40 stable control ids (ok / ko / not measured / not applicable) with dated sources: reputation, checkout path (stops at the payment page), reviews and claims, AI visibility, DNS/e-mail auth, JS key leaks, passive security, Lighthouse mobile; guarded French PDF report (5-6 pages) and registry comparison. Async: typically 10-15 min (8-12 min of work measured) plus queue. Pay on delivery: settled only if the PDF is delivered; if Bierus guardrails block the report, nothing is delivered and nothing is charged.

Signed passive website proof: page reachable, TLS certificate, http→https, response time, title, mixed content, real 404, internal links sample, optional expected text. ok/ko/not_measured + EIP-712 attestation.

Signed passive SEO proof: SEO module scores (technical, content, links, local, AI visibility), title/meta lengths, canonical, single h1, lang, JSON-LD, indexable, sitemap. ok/ko/not_measured + EIP-712 attestation.

Signed PASSIVE security basics: TLS 1.2+, certificate expiry, HSTS, CSP, framing, nosniff, referrer policy, version disclosure, cookie flags, known-vulnerable JS versions in script URLs, mixed content, SPF/DMARC, security.txt. No scanning.

Signed passive checkout-path proof for a store or product page: price/currency/availability, add-to-cart control, cart page, checkout links over https, payment provider, terms/returns/privacy/legal pages reachable, contact. Nothing added to cart, no payment.

Full signed delivery verification: website + SEO + security basics (+ checkout if store=true) + the client's acceptance criteria (expected texts, pages that must answer). One verdict pass/partial/fail and one EIP-712 attestation over all measurements. Async: job_id + free result_url.

Trust decision (trust/caution/avoid + score) for one paid agent provider: x402 offer, MCP, A2A card, 3 unpaid availability probes, domain reputation, OFAC check of payTo, ERC-8004 identity and agentWallet = payTo on Base.

Compare 2-5 paid agent providers with the same measured checks and rank them (decision, budget, trust score, price, latency); returns the recommended provider and why.

Readable vendor due-diligence report: reputation, sanctions (OFAC/UN/EU/UK), product recalls, EU-Ready, email authentication, product offer; proceed/review/block, Markdown report, signed evidence hash. Async if slow (job_id + free result_url), cached 24 h.

Geocode one US street address with the U.S. Census Bureau: standardised address, lat/lon, state, county, census tract, block group, ZCTA, metro area, congressional district (official GEOIDs). No match = not charged.

UK postcode lookup (ONS Postcode Directory via postcodes.io): lat/lon, country, region, local authority, ward, parliamentary constituency, NHS ICB, police force, LSOA. Unknown postcode = not charged.

Fetch and validate a peer agent's A2A Agent Card (v1.0 / v0.3): fields, skills, interfaces, auth, signature, reachability. Score 0-100 + issues.

Real MCP Streamable HTTP handshake (initialize + tools/list, no tool call): reachability, protocol version, tools, schemas, latency, OAuth metadata.

Pre-payment check of an x402 endpoint: one unpaid request, decodes the 402 offer (v1/v2): network, USDC or not, USD price, payTo, testnet, red flags.

Agent-ready score 0-100 (A-F) of a website or API: AI-bot access, llms.txt, A2A agent card, MCP manifest, x402 discovery, OpenAPI and agentic-commerce markup, with fixes ranked by impact.

Architecture plan + installation checklist for one AI-run business: clone=agency (AI sales-agent agency), trading-house (AI B2B trading house) or api-store (API store for AI agents). Components, data flows, build phases, done-when checklist, go-live checks. No source code, no revenue promise. Unknown clone = not charged.

Validate one email address without sending mail: syntax, MX, disposable, free webmail, role account, SPF/DMARC. Returns deliverable/risky/undeliverable/invalid with score.

Audit a domain's email authentication: MX, SPF, DMARC, DKIM (20 selectors), MTA-STS, TLS-RPT, BIMI and domain age. Returns an A-F grade with concrete fixes.

Evaluate a deliverable (text, JSON or URL) against a job spec (free text or JSON criteria): verdict pass/partial/fail, score, checked criteria, and a signed EIP-712 attestation whose digest is the ERC-8183 complete/reject reason. No funds held.

Verify an attestation token issued by evaluate_deliverable: recovers the EIP-712 signer, checks it is our evaluator, returns verdict, score, jobId and the bytes32 reason.

Before buying or selling a product in the EU: Safety Gate alerts (barcode or brand+words), GPSR manufacturer / EU responsible person on the page, seller sanctions (OFAC/UN/EU/UK) and price at the ECB rate, with a ready/review/block decision.

Risk signals for a fragrance listing: sales channel, price per ml, listing words, seller domain and EU Safety Gate. Does not authenticate a physical bottle. Provide url, or brand and seller_domain.

Convert an amount between two currencies at the official ECB reference rate, today or any date since 1999, incl. CFA franc and Gulf pegs. Returns rate, amount, rate date.

Daily official ECB exchange rates for a currency pair over up to 366 days, with min, max, mean and % change. Useful for invoicing, hedging checks and reporting.

All official ECB reference rates for any base currency on the latest or a given fixing date, including pegged currencies (XOF, XAF, AED, SAR). One call, full rate table.

Bundle before paying: verified price/stock (schema.org), seller trust score (RDAP, TLS, DMARC, policies, phishing lists) and recall status (CPSC, openFDA, RappelConso) for a product URL, with a proceed/caution/stop decision.

Verified price, currency, availability and seller of a product page URL from its schema.org JSON-LD / microdata / OpenGraph data. robots.txt respected; blocked or unpriced pages return 'unavailable' (not charged).

Search official recall notices (CPSC, openFDA food/drug/device, RappelConso FR) by product, brand or model; filter by market and period.

Exact recall check for one EAN/UPC/GTIN barcode (check digit validated) across RappelConso, CPSC and openFDA.

Screen a person or company name against OFAC SDN, UN, EU and UK sanctions lists in one call (fuzzy, aliases). Returns matches with score, list, programs, countries.

Check a crypto address (BTC, ETH/EVM, TRON, LTC, XMR, SOL and more) against OFAC SDN digital currency addresses. Returns listed true/false and the sanctioned entity.

Trust score 0-100 for an online store domain or URL: domain age (RDAP), HTTPS, MX/SPF/DMARC, return policy and contact, Tranco rank, phishing lists, scam patterns. Short JSON with risk, advice, red_flags, reasons.

Technical SEO audit of a URL: HTTPS and redirects, www duplicate, canonical, noindex, title/meta/H1, viewport, hreflang, Open Graph, sitemap and robots.txt, soft 404, response time, compression, images alt, schema.org, JS-only content. Score 0-100 + ranked fixes.

On-page keyword and content analysis: focus keyword (given or detected) placement in title/H1/meta/first 100 words/URL, density, top terms and phrases, headings outline, FAQ questions, word count, readability. Score + fixes.

Internal linking audit: crawls up to max_pages same-site pages (robots.txt respected, 30 s cap): broken internal links, orphan pages vs XML sitemap, click depth, dead ends, generic/empty anchors, internal nofollow, duplicate titles, missing meta descriptions.

Local SEO / listings readiness from the website: phone (tel: links), postal address, e-mail, Organization/LocalBusiness JSON-LD (address, telephone, geo, hours, sameAs), Google Maps/Business and review-platform links, social profiles. Score + fixes.

GEO audit - can ChatGPT, Claude, Perplexity, Gemini cite this site? AI search/user/training bots allowed in robots.txt, text readable without JavaScript, schema.org, metadata, llms.txt, sitemap, agentic-commerce signals. Score + ranked fixes.

Full SEO + GEO audit in one call: technical, keywords and content, internal links (12-page crawl), local presence and AI visibility, weighted 0-100 score and the 12 priority actions across all areas, with module details.

Trust Trio: A2A agent card + MCP server probe + x402 payment-offer check of one AI agent in a single call (no payment made to it). Returns trusted/partial/untrusted, a trust score and every issue.

Verify a USDC payment on Base: tx succeeded, USDC sent to the expected recipient (and from the expected sender), at least min_amount, enough confirmations. Returns verdict + decoded transfers. Unknown tx = not charged.

Current USDC balance of an address on Base or Base Sepolia (balanceOf on the official Circle contract).

Vendor due diligence in one call: seller domain reputation, legal-name sanctions screening (OFAC/UN/EU/UK), product recalls (barcode or keywords) and EU-Ready (Safety Gate, GPSR, ECB price). Returns proceed/review/block with reasons.

Compare up to 1000 caller-supplied invoice records for repeated supplier/reference/document identity and conflicting amounts or currency. Exact decimal strings; no external calls, accounting certification or payment decision.

Compare two supplied JSON exports using unique string key fields. Report additions, removals and changed fields, keeping missing/null/boolean/number distinct. No database access or writes; source export completeness is not established.

Order up to 1000 supplied agent events in UTC, preserve undated events, remove identical retransmissions and reject conflicting event IDs. Evidence links are references only; chronology does not establish causality or clock accuracy.

Evaluate supplied observation timestamps against caller-declared TTL and the server clock, or an explicitly supplied historical reference. Return stale/within_declared_ttl/future_observation/unknown. Does not authenticate timestamps or establish underlying fact freshness.

Inspect up to 1000 supplied product fields and sources: missing references, declared expiry, future or undated observations, and content identity hashes. References are never fetched; neither source origin nor support for a field value is authenticated.

Normalize exact decimal quote amounts using supplied currency rates. Up to 1000 total line items. Missing shipping, tax or other costs stay unknown. Rank only complete quotes for identical supplied item-ID/quantity baskets; no rate verification, fiscal advice or order.

Compute UTC monthly cohorts and one declared renewal cycle per supplied subscription. Eligible at supplied due date plus grace; a matching confirmation is a declaration, never proof of collection. Up to 1000 subscriptions and 1000 events. No revenue, MRR, ARR or certain churn inferred.

Diff two supplied OpenAPI 3.0.x/3.1.x documents: operations, parameters, response codes and a listed inline JSON-schema subset. At most 1000 operations/document, 12 schema levels and 4000 compared schema nodes. Unresolved references and excluded semantics remain explicit; no compatibility certification or deployed API verification.

Compare two supplied dated ingredient lists for the same declared product: added/removed normalized names, order and exact declared percentage changes. Up to 1000 ingredients/list; Unicode NFKC/case/whitespace normalization only. No synonym, chemical equivalence, toxicology, allergy, medical or regulatory conclusion.

Compare up to 100 supplied demand lines with 1000 supplied lots, at most 5000 same-item comparisons. Exact decimal quantity, same declared item ID/unit and exact required attributes; missing attributes/availability remain unknown. Lines are independent: no joint allocation, conversion, substitution, reservation or order.

Intersect supplied availability for 1-100 participants, up to 1000 total intervals. Explicit offsets and at most microsecond precision; optional IANA zone is an assertion that supplied offsets match that zone, not a display-zone setting. Return continuous UTC windows for the declared duration. No calendar access, hold, invitation or booking.

Diff supplied snapshots of one declared product and trace changes through supplied content-to-field dependencies. Up to 1000 fields/snapshot, 1000 content records and 10000 dependency references (100/content). Missing edges stay unknown; map completeness and external content truth are not established. No content rewrite or publication.

Simulate supplied daily demand and planned receipts with a declared reorder-point/order-up-to policy, lead time, minimum order and exact lot multiple. Up to 10 scenarios, 365 contiguous days/scenario and 2000 total days. Net shortages carry as backlog; receipts and zero-day virtual orders arrive before demand. Not a demand forecast, supplier-capacity check or purchase.

Reconcile up to 1000 supplied orders and 1000 uniquely identified delivery events at an explicit as-of time. Exact same-unit quantities, deadline, partial/completed delivery, overdelivery and declared cancellation; unknown deadlines remain unknown and future events are excluded. No logistics access, reminder, penalty, refund or proof of actual delivery.

Compare up to 100 supplied reservation confirmations with 1000 supplied registry rows, capped at 10000 resource comparisons. Exact reservation/resource IDs and UTC intervals; expose missing/ambiguous records, held/cancelled status and overlapping confirmed records. No live availability query, fraud finding, hold, cancellation or booking.

Compare supplied numeric catalogue fields aligned by exact product, variant, field ID and required locale. Explicit decimal separator, Unicode decimal digits, no grouping; exact mg/g/kg, ml/l and mm/cm/m conversions. Up to 1000 records, 100 fields/record, 5000 total fields and 10000 comparisons. Missing/unknown/noncomparable values stay explicit. No prose extraction, semantic translation evaluation, currency conversion or catalogue edits.