Paid services on Base matching “action”

AI agent action safety: one-cent deterministic preflight for every consequential agent command. Returns risk, matched rule ids, and an exact machine-readable escalation call: full DestructGuard evidence for medium risk or the complete Action Safety workflow for high and critical risk.

Avoid unnecessary browser launches with a lightweight preflight for AI agents. ZeroWorker inspects public pages before browser automation and returns static forms, field constraints, CAPTCHA/SPA signals, DNS/public-network safety checks, and a 3-state routing verdict: http_candidate, browser_likely, or undetermined. Use it to choose direct HTTP or escalate to a browser. No API key required. $0.003

DCL Trust Oracle. Call only when the text must include the substring AI and must not include "I cannot be held responsible" or "no guarantees". POST JSON {"response","agent_id"}. COMMIT means those checks passed and the action may proceed. NO_COMMIT means do not execute the checked action. Not a tool-call guardrail, prompt-injection detector, or jailbreak screen; use /evaluate/fast for the phrase

Call after your agent completes an action it may later have to prove: seal the hashes of its input and output (only your action label and meta are published) into GBLIN's signed append-only transparency log and get a portable receipt: Ed25519 signature, RFC 6962 inclusion proof, C2SP signed checkpoint; root anchored daily on Base (EAS). Proves existence and time, not correctness. Free reads and de

Independent pre-execution control for consequential autonomous-agent actions. Evaluate a proposed payment, tool call, send, write, publish operation, API action, or other external side effect before execution; return the required approval or human-review boundary and verify that risk stays within the declared limit. 3 bounded free preview calls are available via extensions.humanmirrorPreview.

LONG Events events API: global electronic-music event discovery with structured artists. Actions: discover, list, stats, catalog_stats, spotlight_candidates, get_sets, get_now_playing, get_schedule, search_artists, get_artist, get_artist_events, list_artists. Artist-action identity objects include nullable mbid and verified spotify_id; artist event payloads include the resolved closest-to-purchase

Agent guardrail decision engine. Call once before every agent action; returns a single decision — proceed, slow down (with a reason and wait time), or stop — based on cost budget, chain depth, step cap and retry budget, and request volume pressure. Policy thresholds are configured separately via /policy; this endpoint only reports the decision for a single action.

Lint a GitHub Actions workflow: actions not pinned to a commit SHA, missing or write-all permissions, pull_request_target with PR head checkout, script injection via event fields in run, secrets on the command line, curl|bash, self-hosted runners, deprecated set-output.

Two directions over query strings. action='parse' decodes a query string (with or without a leading '?') into an object, collapsing repeated keys into arrays. action='build' encodes a params object into a query string, expanding array values into repeated keys; set sort=true to order keys alphabetically.

Add-to-cart action experiment plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Agent Decision Signal. Market intelligence for autonomous AI agents deciding what emerging agent-economy opportunity, infrastructure trend or research signal to investigate, build, monitor or deprioritize next. Returns a deterministic action with confidence, evidence, freshness, next action, stop conditions and provenance.

SCOPRI Failure Intelligence — South Korea pre-departure decision API for AI agents. Returns GO/CHECK/HOLD plus GO_WITH_PREP, source-backed failure modes, severity, rescue actions, nearby food/sight fallbacks, navigation and bookable next actions.

Accessibility findings — Numeric interval filter + Secondary-measure weighted mean: Numeric interval filter + Secondary-measure weighted mean for supplied accessibility findings records (findings, resolved_findings). Up to 200 rows; 2 independent reports using shared local analytical engines. No live lookup, prediction, professional assessment or external action. 0.01 USDC includes 2 supplied-data

Attested work record for mixed human/robot/agent crews: seal who (or what) did which action, the outcome, and any deviation from plan — the operational log entry that survives an incident investigation or insurance dispute. ML-DSA-65 signed, Hedera-anchored, independently verifiable by any party.

US Congress bill status from the official GPO GovInfo BILLSTATUS bulk XML (the GovTrack API it replaces has closed): title, sponsor, introduced date, latest action and official congress.gov link for one bill by congress, bill type and number. Covers congresses with BILLSTATUS files (119 at test time).

Publisher discovery repair plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Get one Polymarket versus Kalshi gap card with the topic, both yes prices, gap cents, a fee-adjusted net edge, buy and sell venues, and a suggested action. The fee-adjusted net edge is the number a trading wallet acts on. $0.25 USDC. Inline JSON. Includes a signed Ed25519 receipt you can check with the published key.

AI & automated-systems governance regulatory & enforcement changes since a timestamp, merged from the Federal Register (rules, agency notices, executive orders), White House actions, FTC AI enforcement, the EU AI Office & Commission, EU legal acts, and NIST standards activity. Each item scored 1-10 for impact, tagged with its originating regulator (detail.origin), with primary-source links.

Scheduled market-moving events for the next 7 days by default (?days= up to 90): US data releases with release times (CPI, jobs, GDP, PCE, PPI), FOMC, ECB and Bank of Japan decisions, Treasury auctions and dated crypto and regulatory milestones, each with importance 1-3 and official source. Use before any trade or scheduled action to know what is on the calendar. From official schedules, refreshed

Business Frameworks · business-frameworks/risk/decide/hurdle@1.3, applied — POST the long-bond yield and two or three comparable asset betas; get r for this business — its cost of capital, the discount rate — with the sub-$5M probability rule and the concentrated owner's stated premium applied. Deterministic (the node's rule, no model): returns figures, verdict, action and check with the 170-token

Entry point to the x402 Carbon Retirement API on Base. Returns every endpoint you need plus a live snapshot of the top 3 carbon classes and marketplace listings by liquidity. Discover, quote and certificate are free. Retiring is paid: each retirement costs the credit price plus a fee, sent from your own wallet (prepare/retire) or relayed from a signed USDC authorization (prepare-auth + POST action

Evaluates caller-supplied telemetry samples against declared reaction-time, actions-per-second, movement-speed, and impossible-event rules. Flags are review signals only; the service does not identify software, inspect a device, establish intent, or justify an automatic ban.

MCP security: catch a rug pull or tool poisoning between two tools/list results of the same MCP server — the version you approved and the one it serves now. Flags instructions aimed at the model, override and concealment wording, credential and wallet paths, covert actions, hidden Unicode, new URLs and addresses, a dropped readOnlyHint, new command or path parameters and look-alike tool names; ver

MIDAX402: Evidence+ x402 intelligence with expanded corpus retrieval, local risk brief, contradiction scan and concrete action plan. We do not grade our own answer: the verdict is answered or needs_more_data (grounded in the corpus or not); evidence_grade (thin/moderate/broad) grades that evidence, auditable via retrieved_corpus_ids. confidence_score is DEPRECATED, still served as a band projectio

Restore all four needs in one care action. Any verified payer may care for any hatched target.

Execution preflight: a chain-neutral ALLOW/CAUTION/BLOCK data-sufficiency decision for one declared action. A complete BLOCK result is charged; settlement occurs only after a successful response.

Classify a caller-supplied operation claim against caller-supplied evidence under deterministic rules and return a machine-readable handoff receipt. Use this when an orchestrator needs a consistent completion state before accepting an agent's work. VERIFIED_COMPLETE means the submitted evidence supports the submitted claim; QSL does not independently observe the underlying real-world action.

Lead verify for one NL or BE sales lead: is it a real, active company? Checks the KVK or KBO register and cross-checks what the lead holds: VAT with VIES, mail server and disposable domain, IBAN country and bank (not the holder), and the company name against the OFAC, EU and UN sanctions lists. Returns a verdict, a 0-100 lead score and flags, each with one action. An input not given is not checked

Token risk / token safety check for Base and BSC (BNB Chain) tokens: honeypot detector via live buy/sell simulation (honeypot.is, cross-checked with GoPlus when available), buy tax / sell tax, contract security (mint, pause, blacklist, proxy, owner renounced), holder concentration, liquidity, pool age, LP burn. Returns verdict low/medium/high/honeypot, 0-100 risk score, action and plain reasons. R

Screen one address (EVM, BTC, Tron, Solana, DOT, XRP, XLM, DOGE, LTC, DASH, STX, TON, Cosmos or wax:account) against the OFAC SDN list, Tether/Circle freezes (EVM, Tron, Solana) and C3 reports. Returns action BLOCK (OFAC SDN match), REVIEW (reported or frozen; current freeze = HIGH) or ALLOW_NO_REPORTS, riskScore, riskLevel, sanctions, freezes, reports, related domains, co-occurring addresses. NON