All projects matching “agents”

Check a public website's security hygiene before your agent links to it, recommends it, or sends data to it. One URL in, deterministic JSON out: HTTPS and redirect chain, HSTS, CSP, X-Frame-Options, X-Content-Type-Options, Referrer-Policy, Permissions-Policy, security.txt, robots.txt, sitemap.xml, plus plain-language notes. Private, localhost and raw-IP targets are rejected; error responses are no

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

Before your agent onboards, pays, or contracts with a counterparty: screen the name against the U.S. Treasury OFAC sanctions lists (SDN + Consolidated non-SDN, synced every 6h) for $0.01. Benchmarked 114/114 sanctioned names found with zero false positives on a 152-case adversarial corpus of misspellings, word-order swaps, and transliterated aliases. Ranked candidates with confidence 0-100, progra

Solana token safety check: verdict (safe/caution/avoid), 0-100 risk score and reasons from mint/freeze authority, Token-2022 extensions, holder concentration, age and DEX liquidity. Use when an agent is about to buy, swap, accept or recommend an unfamiliar Solana token. Not financial advice.

ISBN-10/13 check-digit validate + Open Library metadata (polite User-Agent).

AGENT CREDIT REPORT: lender-grade credit passport for a Base wallet/agent. POST body: {"target":"0x…"}. Returns score 0-100, risk flags, Base vitals, ERC-8004 identity signal, KHOTEM payment history, indicative service-credit limit and sealed report. Not a cash loan — underwriting evidence for lenders and service-credit offers.

Machine-consumable web3 integration-risk decision for buyer agents ($0.10).

Sign up for Aient as an autonomous agent by paying once: your wallet address becomes the principal, an organisation is provisioned, and the response includes the publishable telemetry-ingest endpoint plus a first environment key. Idempotent per wallet.

Website trust check: verdict (trustworthy_likely/caution/risky) with reasons from domain age (RDAP), DNS (A/MX/NS), HTTPS reachability and redirect chain, security headers, phishing/malware list snapshots, brand lookalike/typosquat detection, tech fingerprint and page title. Use when an agent is about to open, click, submit credentials or payment to, recommend or trust an unfamiliar URL or website

Launch announcement for AI agents: give a product URL, get a ~400-word AP-style press release drafted from the page and published on a public, search-indexed newsroom page (IndexNow ping to Bing/Yandex included). Synchronous, ~20s. You are only charged if the release is produced.

Wikipedia page summary via REST (keyless, User-Agent required). title (+ lang) → extract/thumbnail/urls.

Agent-readiness check for a public site: robots.txt AI-bot rules, llms.txt, JSON-LD schema, OpenAPI/MCP discovery, /.well-known/x402. Deterministic 0-100 score + fixes. Max 6 capped public GETs. Bad url → 400, unreachable host → 422, both charged:false (checked before settle).

GitHub repo metadata (keyless, User-Agent required). owner/repo → stars/forks/language/license. Soft-fail 403 rate.

Discogs release/search (keyless; Discogs User-Agent). POST {q|query|artist|release_title}. Unpaid empty → 402; after settle empty/invalid → 400 charged:false. Soft disclose musicbrainz-lookup.

Your agent surveys real people, anywhere. Pay-per-call MCP server backed by Flashpoint.AI's panel network — demographics, synthetic respondents, full survey lifecycle, and AI-powered analysis. Per-call prices are listed in `tools` below; settlement on Base mainnet via x402.

The daily history of one agent record: dealings, independent payers, concentration and delivery over time.

Return a compact agent-readiness score for OpenAPI or MCP input.

Dedicated satellite tracking API for agents: list CelesTrak TLE catalog groups (ISS, weather, and more), get live propagated positions for a whole catalog group, and predict the next pass over an observer latitude/longitude using NORAD catalog IDs. Outbound CelesTrak fetch only; no shell access.

SEC EDGAR XBRL companyfacts (keyless; outbound User-Agent required). POST {cik} (normalize/zero-pad). Unpaid empty → 402; after settle empty/invalid → 400 charged:false. Disclose adjacency: sec-ticker-lookup (ticker map ≠ companyfacts).

BICScan pre-transaction risk check: one paid call screens the counterparty address, the dApp URL/domain and the EVM token contract an agent is about to send to, sign on or approve, and returns an allow/warn/block verdict with reasons (sanctions/OFAC, phishing domains, scam tokens, BICScan risk intelligence). Addresses on EVM chains, Solana, Bitcoin, Tron, XRP and ICP; TON is not supported.

MusicBrainz WS/2 lookup/search (keyless; User-Agent required; 1 req/s). entity + mbid OR query → trimmed JSON.

Create a custom email mailbox at @clawmail.xyz for AI agents and LLMs

AI Web Extractor — turn ANY url into clean, LLM-ready markdown. POST {url}; get the main content as markdown (boilerplate/nav/ads stripped) with title, description, and links. The scrape / read / url-to-markdown primitive for RAG and research agents. Fast, cheap, x402-native.

Payload Check: data-quality filter for agents. Send any payload (tool/API output, scraped page, LLM answer, generated code, JSON, CSV) and get a 0-100 quality score, pass/warn/fail, tags and concrete issues: invalid or truncated JSON (with auto-repair), JSON Schema mismatches, syntax errors, bot-challenge/captcha/404 scrapes, LLM refusals, placeholders, repetition loops, mojibake. Deterministic, n

Wikimedia REST per-article pageviews (keyless). POST {article|title, start, end, project?, access?, agent?, granularity?}. Unpaid empty → 402; after settle empty/invalid → 400 charged:false. Soft disclose wikidata-entity / wikipedia-summary.

DLF agent API key — $0.10 unlocks 10,000 mcents (1:1 starter) + $0.05 activation bonus unlockable by labeling 5 images

Capture a public HTTPS page as a bounded PNG screenshot for an agent without a browser. Returns a job to poll, then a private image and capture facts; saved retrieval is free.

Settlement-backed machine evidence for autonomous agents. Returns a signed-payment transaction reference and machine-readable proof after exact USDC settlement.

LEGIT: trust scores and organic demand intelligence for the x402 agentic economy. Created by GONNA.

Pay an owned Mondoir catalogue quote in native USDC, including shipping and applicable VAT. Agent bearer authentication and a fresh quote are required.