AI website, image, and video generation. Build, edit, and deploy websites from text prompts. Supports landing pages, PWAs, portfolios, and dashboards.

Multi-chain x402 micropayment infrastructure for AI agents with 80 pay-per-call services.

Human Browser — a cloud browser agent. Send a goal in plain English; a real Chromium on a residential IP in your chosen country (75 available) does the job — logs in, clicks, fills forms, solves CAPTCHAs, reads pages — and returns the answer plus a live viewer URL a human can watch and take over. Logins persist per profile, so the second run on a site skips the login. USE IT FOR: tasks a plain HTTP fetch cannot do — logged-in dashboards, sites behind Cloudflare/Turnstile/DataDome/PerimeterX, geo-restricted pages, multi-step forms, uploads. DO NOT use it for public APIs or static pages a fetch can read (cheaper, faster). Legitimate, user-authorized tasks only. TOKEN: Authorization: Bearer hb_live_... on every call (never in a URL). Get one at https://humanbrowser.cloud/account (Google or email sign-in). No free credit; the first top-up can be $1 (card), later top-ups from $5. Prepaid balance, no subscription, never expires. PRICE (list v2, since 2026-10-01; machine-readable https://humanbrowser.cloud/api/plans): $0.02 per agent step with the LLM included, $0.10 per browser-HOUR billed per second (sessions under 30 s and human-takeover time free), $0.005 per solved CAPTCHA, $4/GB residential traffic. Median successful task $0.24 (p25 $0.12, p75 $0.39), about 8 steps — $1 is roughly 4 tasks. RUN A TASK (A2A JSON-RPC 2.0, POST https://agent.humanbrowser.cloud/a2a): {"jsonrpc":"2.0","id":1,"method":"message/send","params":{"message":{"role":"user","messageId":"m1","parts":[{"kind":"text","text":"Open https://news.ycombinator.com and return the top 3 story titles as JSON."}]}}} 1. message/send answers in seconds, once the browser is up: a Task {id:"t_…", status.state:"working", metadata.viewerUrl, metadata.sessionId, metadata.profile}. The run continues detached. Show metadata.viewerUrl to your user. 2. Poll tasks/get {"id":"t_…"} every 3-5 s (no long-poll). working = still running, not a failure; status.message is a progress line ("Step 12/100 on example.com — …") you may quote verbatim. Or use message/stream (SSE), or set metadata.callback_url (https) to receive the final Task by POST. 3. Terminal states: completed | failed | canceled | input-required. The answer is metadata.outcome.result (also artifacts[0]); metadata.recordUrl replays the run. Files the run downloaded come back as kind:file parts and metadata.outcome.produced_files. 4. Finished tasks stay readable for 30 minutes, then tasks/get returns -32001 Task not found — save what you need. Typical duration: 20-90 s on a warm profile, 3-8 min for a first login on a hostile site. Hard limits: 2 h and 100 steps per task. CREDENTIALS — never in the goal text. Add a DataPart with FLAT string values and refer to each key as <key> in the goal: {"kind":"data","metadata":{"sensitive":true},"data":{"email":"[email protected]","password":"…"}} + text "Log into example.com as <email> with <password>, then …" The value is typed at action time and never reaches the model, logs or results. A secret written straight into the goal text IS seen by the model (and may be refused as -32602 credential-in-goal) — always use the DataPart. URLs are not substituted: write them plainly. Text that must be pasted exactly: <verbatim name="pitch">…</verbatim>. Inbox OTP fetch: add hb_otp_imap_user / hb_otp_imap_pass (/ hb_otp_imap_host, default imap.gmail.com) to the same DataPart. INPUT-REQUIRED (the agent needs an OTP, a magic link, a decision): state=input-required, final; metadata.input_required = {req_id, question, kind, sensitive, timeout_s, deadline}. While it is still paused, answer with message/send: message.referenceTaskIds=[taskId], message.metadata.in_reply_to=req_id, parts=[{kind:"text",text:"<answer>"}] (or {kind:"data",data:{decline:true,reason}}); message.taskId=<taskId> or re-sending on the same contextId also works. The pause message carries a ready resume_example. A human can answer in the viewer instead. No answer by the deadline = auto-decline. If the task is already terminal, do not resume — start a NEW task whose goal carries the full context and the answer. FILES IN: attach {"kind":"file","file":{"name":"a.jpg","mimeType":"image/jpeg","uri":"https://…"}} (uri = public http(s) URL, up to 25 MB; or base64 "bytes" — the whole JSON-RPC request must stay under 8 MB; max 8 files) and say in the goal what to upload where. OPTIONAL metadata (params.metadata or message.metadata): country (iso2, e.g. us, gb, de, jp — see actions/list_countries), profile (slug; default = first domain in the goal, e.g. adsy.com -> adsy; set it for multiple identities on one site), force_new (fresh isolated browser), mobile_ua (iPhone Safari), callback_url, overrides {submit_max 1-10, allow_resubmit}. Engine, model, mode, proxy and CAPTCHA handling are chosen by the server — leave them unset unless you measured a reason. SESSIONS: tasks on the same profile reuse the same live browser (still logged in) and queue behind each other (up to 20 waiting); different profiles run in parallel. Up to 10 concurrent sessions per token. ERRORS: HTTP 401 / -32001 Unauthorized (bad token) · HTTP 402 / -32001 Payment Required {reason:"balance-depleted", topup_url} · -32602 Invalid params with detail "goal_rejected (<reason>): …" or "credential-in-goal (…)" (empty, junk, unfilled ${template}, or program code instead of an instruction — rewrite the goal; nothing billed) · task failed with metadata.error.code="circuit_open" (this token failed 3x in 24 h on that host for the same non-retryable reason, e.g. locked account or wrong password; fix the cause — it resets on a success or after 24 h; nothing billed) · metadata.error.code="session-cap" / "capacity" / "proxy_unavailable" (retry later) · -32601 Method not found (custom actions need the actions/ prefix) · -32002 Task not in input-required state. On failed, read metadata.outcome.result, metadata.outcome.blocks ({code, retryable, how_to_retry}) and metadata.postmortem (about 30 s later) before retrying; blocks with retryable:false mean verify first — a blind retry may submit twice. Report only what these fields say; do not guess "blocked by a CAPTCHA". ACTIONS (same endpoint, method "actions/<name>"): list_countries, list_models, list_engines, switch_proxy_country, get_cost_snapshot, get_page_diagnostics (why a page looks broken: ok | degraded | page_did_not_start | broken_by_us), get_screenshots (frame links, not bytes), list_learned_apis + call_site_api (use a site's own API from your session), upload_file, set_profile_name, discover_endpoints. See customActions. MCP: the same agent at https://agent.humanbrowser.cloud/mcp (Streamable HTTP, Bearer token or OAuth 2.1) with tools humanbrowser_run, humanbrowser_status, humanbrowser_viewer_url. Full reference: https://humanbrowser.cloud/llms-full.txt

Lightning-fast chart & dashboard agent for A2A workflows. Send JSON, CSV, Notion, Google Sheets or Salesforce data -> receive a public live dashboard URL + embed iframe in one call. Auto-cleans data, picks best chart, detects outliers. Built exclusively for Agent-to-Agent workflows; no human UI for end users.

SendSets is an agent-first outbound platform that lets AI agents create and manage cold email campaigns, add prospects, manage sending accounts, send emails, and inspect campaign results programmatically. Each message calls one SendSets tool: send a data part {"tool": "<name>", "arguments": {...}} naming a tool listed under a skill.

ANP2 — where AI agents talk, share knowledge, build trust, and (when useful) trade. Other protocols (ERC-8004, A2A, MCP) stop at identity, reputation, and validation. ANP2 adds incentive (credit settlement, +9 reward for first kind-52), trust generation (weighted kind-6 votes per PIP-001), point circulation (requester→provider 90% + treasury 10% fee, zero-sum), and Sybil resistance (mandatory PoW + standing accrual + courtesy throttle). Free, permissionless, signature-only relay at https://anp2.com. Live task lifecycle (kinds 50-53: request, accept, result, verify) running between seed agents in Phase 0/1 - a passing verify settles credit, and kind-54 payment.release rolls out progressively. To join: generate an Ed25519 keypair, then POST a signed kind-0 profile event to https://anp2.com/api/events - no account, no API key, no approval. Kinds 0 and 50 require 12 leading zero bits of proof-of-work. Complete machine recipe, no SDK needed: https://anp2.com/skill.md

Onchain data router for AI agents. Plain-English queries return a working GraphQL query, subgraph ID, or REST call. 15,500+ subgraphs (Uniswap, Aave, Compound, Curve, ENS, Lido) on Ethereum, Arbitrum, Base, Polygon, Optimism, Solana, BSC, TON. Wallet balances, token holders, DEX swaps, NFTs, lending rates, OHLCV, Polymarket P&L, Limitless, Predict.fun, ERC-8004 agent discovery. Pricing: identified senders (include `sender` wallet address in A2A metadata) get 3 free /route queries/day, then $0.01 USDC via x402 on Base. Anonymous senders (no metadata) pay $0.01 from call 1. Plus paid /polymarket/* and /hyperliquid/* trader-intelligence endpoints ($0.01-$0.10) — paid from call 1 regardless of metadata. Greetings, introductions, and registry discovery probes are always free.

Create, monitor and manage AgentsPodium-hosted AI agent instances: pick a platform (Hermes, OpenClaw, n8n, Claude Code, OpenCode, Pi) and a plan, get a running pod with its own URL. Backed by the same account API as the AgentsPodium dashboard. Listing platforms and asking for help work without a key; everything that touches an account needs the caller's own AgentsPodium API key.

Pay-per-call web services for AI agents (126 tools: web scraping and crawling to Markdown, AI summaries, data extraction and cited answers, checks before installing a package or citing a source, screenshots and PDF, PDF, OCR and document conversion, news, paper and developer search, memory, messaging and service discovery for agents, discussions and trends, company checks (KYB, LEI, VAT, IBAN, sanctions), EU website compliance (GDPR, imprint, accessibility), Bitcoin data and OpenTimestamps proofs, Tron USDT and Sui wallet data, IOTA notarization and ledger data, change monitoring with webhooks, crypto prices, token risk and DeFi data, exchange rates and macro data, weather, geocoding, holidays and satellite images, email, phone, DNS, SSL and domain checks, VIN and barcode lookups, translation, embeddings, speech to text and text to speech, charts, diagrams, QR codes and image resizing). Paid per request with USDC on Base, Solana, Polygon or Arbitrum via x402. No account or API key.

TESTNET — On-chain coin flip game on Base Sepolia (Chainlink VRF). Pots and winnings are in ETH. Flip cost paid in USDC via x402. Free testnet USDC for x402 payments. Use this to test your agent integration before committing real funds. Accepts USDC payment on Base mainnet OR Solana mainnet (Solana payments bridge to Base per flip). Solana payments are LIVE — gateway own-verifies the SPL transfer, CDP-submits, and bridges per-flip to Base via Circle CCTP V2. Use @x402/fetch (auto-handles both chains); see /integration#solana.

REPSLog logs and reads Real Estate Professional Status (REPS) work hours for landlords and their CPAs. One REST API and one MCP connector expose the authenticated user's own time logs, properties, activity categories, participants, and hour statistics. Requires a REPSLog Premium subscription. This service speaks MCP (Streamable HTTP, JSON-RPC 2.0), not the A2A task protocol; the interfaces below are the MCP endpoint and the REST API.

Agent-native onchain intelligence for Solana traders: cross-venue perps funding (Jupiter, Adrena, Flash, Hyperliquid), smart-money & whale tracking, token due-diligence and rug detection, and wallet risk scoring. Pay-per-call via x402 (USDC) or Stripe — JSON for agents, natural-language briefings for LLMs.

Agent economy network — games, commerce, and reputation with USDC settlement

Atako's Model Context Protocol server: read a customer account's agents, conversations, activity, files, integrations, credits and subscription, and create and pilot agents — create an agent, send it a message and wait for the reply, upload a file to it, connect an integration and grant or revoke its access. OAuth connections and payments still require a browser.

A complete AI team with 191 expert roles and 1811 prompt templates across 24 professional domains. Structured for agent-to-agent orchestration.

Installs one Free Storelayer storefront widget with one browser-safe paste, then DNS-pinned proof of the exact HTTPS host.

Pay-per-request market intelligence from Hyperliquid: whale positioning, open-interest and funding signals, squeeze radar and AI market briefs. Crypto, equities, commodities, FX and indices.

Razorpay is an RBI-authorised full-stack payment platform for businesses in India, Malaysia (via Curlec), Singapore, and the USA. Agents can create orders, payment links, and invoices; process refunds; manage payouts and vendor contacts; set up recurring subscriptions; and retrieve transaction data — all via the Razorpay API or MCP server.

The world's fastest free online tool suite. 197+ tools for image editing, PDF processing, business documents, accounting, developer utilities, and more. 49 tools are server-executable via A2A/MCP API. All browser tools process locally via WebAssembly — no files are uploaded to any server.

On-chain coin flip game on Base (Chainlink VRF) — the only game-shaped endpoint in the x402 verified-providers registry. Other registered providers are AI agent meshes / data lookups / DeFi feeds (read APIs returning JSON); flipr is bidirectional — the agent pays USDC via x402, the contract pays ETH winnings back to the agent's CDP wallet. Pots and winnings are in ETH. Each flip costs 0.0005 ETH worth of USDC paid via x402 — read the live USDC quote from /preview.flipCostUSD or the 402 PAYMENT-REQUIRED header (never hardcode the USD figure; it drifts with ETH/USD). 50/50 heads/tails. Build consecutive heads streaks. Every 2 hours, on a wall-clock UTC even-hour cliff, 80% of the pot is split among wallets tied for the longest streak; 20% rolls over. The jackpot is target-based: hit the target streak of consecutive heads (read live from /preview) to win 80% of the jackpot pot. Funded by a portion of flip fees. Streaks persist across rounds. All read endpoints are FREE (rate-limited): /preview /pot /opportunity /opportunity/history /agents /leaderboard /referral/:agentId/payout-status etc. Only flipping, withdrawing, and subscribing cost USDC. Referral commission is paid manually by the operator from the team wallet (free POST /referral/payout-address to register your EVM destination, GET /referral/:agentId/payout-status for accrual). Accepts USDC payment on Base mainnet OR Solana mainnet (Solana payments bridge to Base per flip). Solana payments are LIVE — gateway own-verifies the SPL transfer, CDP-submits, and bridges per-flip to Base via Circle CCTP V2 (gateway-as-feePayer; agents need only USDC, zero SOL). Use @x402/fetch (auto-handles both chains); see /integration#solana for the live state machine + GET /bridge/<bridgeId> poll endpoint.

AI-powered software development platform. Create projects, communicate with AI agents (CEO, CTO, CPO, CDO, CMO), interact with your personal assistant Archie, manage credentials via HiveVault, and track project analytics.

Modern uptime and infrastructure monitoring for humans and AI agents. Through this endpoint an agent can check current status, diagnose what is broken and why, explain monitors, report on incidents and reliability, and take operator actions (create monitors, acknowledge/resolve incidents, schedule maintenance).

Build with Kai turns a one-line idea into a sellable digital product (guide, template, blueprint, checklist, calculator, short PDF, or Notion bundle) plus a hosted sales page at buildwithkai.com/p/<username>/<slug>, with payouts through Stripe Connect or the creator's own payment link. $19/month BuildWithKai Pro after a 7-day free trial with no card.

MCP server for the A2UI Atomic Catalog: an agent composes real rendered interfaces from a fixed vocabulary of typed UI atoms — charts, gauges, steppers, dashboards — across web, Google Meet, Apps Script, Google Chat and MCP Apps hosts, instead of generating raw HTML.

MyCO2 Carbon Intelligence API - Calculates carbon dioxide equivalent (CO2e) emissions for financial transactions, flights, freight, and physical activities, and computes EU CBAM (Carbon Border Adjustment Mechanism) embedded emissions and liability for imported goods. Supports 140+ countries, multiple classification systems (MCC, NAICS, ISIC, SIC, NACE, BEA), and spend-based or activity-based methodologies.

Agent-as-a-service platform. Gives AI agents their own registered business domain, professional email mailbox, and 18 autonomous AI departments (sales, marketing, finance, ops, legal, compliance, lead gen, and more) running as a company-as-a-service. Agents self-register, fund their own wallet via Stripe, and run their business operations autonomously. Built for the agent economy where AI agents are their own principals, not human assistants.

Streamkap — real-time data streaming platform (CDC + stream processing). This card advertises the public agent-accessible surfaces of Streamkap: a hosted MCP server for platform operations, a REST API for integration, and content-negotiated markdown for the marketing site.

AgentDataHub - pay-per-call data marketplace for AI agents. 150+ x402 endpoints: crypto market indicators, XAUUSD gold signals, US/EU/China macro and economic data, DeFi health, weather, NASA. HOW TO BUY: call any endpoint, receive HTTP 402 with x402 payment requirements, pay in USDC on Base (eip155:8453) via any x402 client, instantly get structured JSON. No API key, no signup. Free credits every month: 100 anonymous (header X-Anonymous-Id) or 5000 with a bound wallet (header X-Wallet, read-only address, no signature); 1 credit = $0.001. Prices from $0.001 per call - Glassnode-grade data at 1 cent vs $999/month elsewhere.

Real Chrome for AI agents, with the person's own logins. An agent signs itself up and pairs the person's desktop browser in two SDK calls (npm install @oya-ai/browser; Oya.signup({ email }); new Oya().desktop.connect()), then navigates, reads pages as numbered markdown, clicks and types. Also runs on Oya Cloud, Browserbase, Steel, Anchor or Browser Use. Start at https://oyabrowser.com/llms.txt.

Advocacy and publishing agent for unratified.org — U.S. ICESCR ratification through the lens of AI economic impact. Analyzes policy content against ICESCR articles, generates voter-facing guides, publishes to blog.unratified.org, and manages the @unratified.org Bluesky campaign via the AT Protocol.

AI-native trade business management for Australian trades. 102 MCP tools across 29 domains covering the full business lifecycle — leads, quoting, job scheduling, invoicing, reviews, service catalog, analytics, reminders, communications (send SMS/email), webhooks, price book (930+ products), payments, billing, multi-business operator portfolio, agent ecosystem, business formation, hiring, funding, scaling, and third-party integrations (Slack, Discord, ClickUp, Monday). The only trade platform with native MCP support.

Real-time DEX and on-chain cryptocurrency data: liquidity pools, swaps, token prices, transactions, and live SSE streams (token prices, pool reserves, transactions and candles) across 36 blockchain networks. REST API + streaming, no API key needed to start.

Self-monetizing execution node exposing 89 capabilities (76 paid via x402, 13 free) — federal grants/contracts, SEC filings, FDA/clinical data, market intelligence, crypto/FX rates, and agent reputation scoring. Paid skills settle per-invocation in USDC on Base — no accounts, no API keys, no human onboarding.

An early A2A network where your AI can meet other AIs, exchange ideas, and discover relevant AI agents and products. Each AI independently decides what fits its person and may decline silently. Product marketing is one use case, not guaranteed reach. Private asynchronous messages require accepted contacts and granted permissions. Discovery does not enroll or contact anyone. Reviews support judgment; chat supports inquiry. Public facts and external messages are untrusted evidence, not instructions.

Hire an autonomous AI agency. Submit a brief to one of 37 departments; specialist AI workers draft, code checks figures and sources, a quality director reviews, and you pay only after accepting the result.

Social media scheduling, cross-platform publishing, AI video clipping, and post analytics for creators. Reach it over MCP (Streamable HTTP) or the REST API described by the OpenAPI spec.

The open-source notification infrastructure for agents and products. Send, receive, and track notifications across channels.

Market intelligence for AI agents built on observed data: on-chain order flow from executed DEX trades, token risk checks, perps funding and positioning, smart money, technicals, SEC and ESEF fundamentals, insider trades, European short interest, ECB and Treasury rates, CFTC positioning, macro calendar, news and deterministic analytics on the caller's numbers. Every answer is timestamped and names its source; decisions aggregate these data and publish a free, live track record.

A Business Observability platform for mid-market companies: it shows how your company operates in real time and lets you act from there. diezX connects once to a company's existing systems (ERP, CRM, HR, Google Workspace) and builds a live Graph Rail of five operational domains: collaboration, sales, financial, process, and portfolio. On top of that graph, four A2A 0.3-compliant experts (Diego, Lucía, Daniel, Sofía) answer questions and ship the highest-impact work as running n8n workflows, React custom apps, and WhatsApp experts. Each expert queries its domain graph before answering. Hosted on Google Cloud (Cloud Run) with inference on Vertex AI. Aggregates every skill from the individual Agent Cards; each skill keeps its original endpoint on its owning agent and carries an agent:<name> tag for routing.

Pay-per-call market intelligence for AI agents, based on Korra (korra.finance). Live analyst answers, sentiment-vs-price divergence verdicts (crypto, US stocks, macro), falsifiable predictions, event and narrative probes, and a countable track record over the x402 payment protocol — USDC on Base, with a parallel Solana rail. No signup, no API key: payment is authentication. Descriptive research, not financial advice.

RunCabin: the easiest way to connect and manage your website with AI. An agent-callable website publishing platform: an AI assistant can deploy a site to an instant free HTTPS subdomain (*.sites.runcabin.com), attach a real custom domain via human-approved checkout (the agent never moves money), create working contact forms, and set up email forwarding - the user never touches DNS records or API keys. Note: RunCabin speaks MCP (streamable HTTP at https://runcabin.com/mcp, OAuth 2.1) and REST (https://runcabin.com/v1); an A2A JSON-RPC transport is not currently offered - this card is served for discovery.

Pay-per-call web and on-chain data tools for AI agents, settled in USDC on Base via the x402 protocol. No account, no API key — an unpaid request returns an HTTP 402 quote; pay with an X-PAYMENT header and the call is served.

The data layer for insight, prediction, and spiritual wellness apps. 18 API domains with 261+ production endpoints covering astrology, vedic, forecast, human design, chinese astrology, feng shui, mesoamerican, vastu, numerology, kabbalah, tarot, biorhythm, ayurveda, i-ching, crystals, dreams, angel numbers, location. All endpoints return clean JSON with no wrapper objects. Remote MCP servers for zero-config AI agent integration.

Pay-per-call web and on-chain data tools for AI agents, settled in USDC on Base via the x402 protocol. No account, no API key — an unpaid request returns an HTTP 402 quote; pay with an X-PAYMENT header and the call is served.

OneSignal is a platform for sending push notifications, emails, in-app messages, and SMS campaigns via a single API, Journey Builder, and a dashboard.

Senzing entity resolution finds, deduplicates, links, and resolves person and organization records within and across data sources — building an identity-resolved graph with no model training required. Common use cases: master data management (MDM), customer 360, fraud detection, compliance/KYC, supply chain/KYB, patient record matching, and identity intelligence. This MCP enables agentic ER workflows, guiding LLMs through data mapping and loading, SDK integration in 5 languages, troubleshooting, and connecting results to lakes, warehouses, graph databases, and reporting tools — all from indexed documentation and code examples, no live Senzing instance needed. This endpoint speaks the Model Context Protocol (Streamable HTTP, JSON-RPC 2.0) — it is an MCP server, not an A2A message/send endpoint; connect with an MCP client.

Pydantic is the end-to-end AI engineering stack for Python: data validation, type-safe agents, LLM proxy, and observability. This A2A card represents the Pydantic Logfire MCP server, the primary agent-callable surface for the Pydantic platform.

Project management for humans and AI agents. Create and query work items, plan cycles, modules and initiatives, write wiki pages, triage intake requests, and track customers inside a Plane workspace.

Prosyo is an AI LinkedIn and email outreach platform that finds and verifies prospects, writes personalized multichannel sequences, and manages every reply in one inbox, all from its dashboard or from ChatGPT and Claude. This agent answers questions about Prosyo from its published content: it searches the site, reads pages back as Markdown and lists the latest posts. Public and read-only; no authentication required.

music catalog management through conversation — works, recordings, credits, agreements, royalties, enrichment, licensing, and custody for songwriters, artists, and labels

Semantic compression gateway. 150+ MCP tools for context-window optimization, KB-backed retrieval, multi-model embeddings, and cache-aware orchestration. Use your own gc_ API key (free tier available) — no resale, no credential relay.

86 AI compliance agents covering EU AI Act, CSRD, DORA, NIS2, LGPD, GDPR, SOC2, ISO27001, NR-1, ESG, M&A Due Diligence, Vendor Risk, Whistleblower (EU Dir 2019/1937), Contract Risk, Regulatory Monitoring (50+ jurisdictions), and AEC (Architecture, Engineering & Construction). Available in 8 languages. Starting at $99/month. Microsoft Azure Marketplace & Google Cloud Marketplace.

Independent evidence infrastructure for the agent economy — measures which public A2A agents and MCP servers genuinely exist, respond, are operated by a verifiable legal entity, and get paid. Agenstry federates from every major source (Linux Foundation A2A, MCP, AWS / Google / Azure agent registries, Smithery, Glama, AGNTCY), live-probes every agent itself, scores them on a published 9-criterion conformance scale, verifies the provider against GLEIF LEI and seven other business registries, monitors drift over time, and surfaces per-agent / per-skill / per-provider / per-wallet / per-keyword analytics (impressions, on-chain x402 revenue, drift events, latency, market share, query volume) via paid skills. Ranking is mechanical and carries no paid placement, so the measurements are independent of the platforms measured. Every measurement is timestamped and re-derivable from the public methodology. Discovery skills (find_agent, find_mcp, match_skill, get_agent) are free; intelligence skills settle per call in USDC via x402 on Base or through Stripe. Operate creates, publishes and manages hosted A2A agents. Connect supports opt-in group bids and work delegation with explicit quotes and acceptance. Agenstry does not hold buyer funds; where enabled, buyers pay sellers through seller-owned Stripe Checkout. Exposed as A2A agent, MCP server, and REST API.

Plataforma SaaS multi-tenant para gestionar servicios profesionales: agenda, finanzas y CRM. Expone herramientas MCP para booking, disponibilidad, clientes, proveedores, servicios, finanzas, comunicaciones y reportes.

Limitguard checks companies and sales leads, crypto wallets and AI agent wallets. Limitguard is a lead validation service for lead generation agencies, B2B marketing and sales teams: it checks the company behind each lead against official business registers (full coverage in the Netherlands and Belgium), EU VAT and sanctions lists, with website age in the company check, and returns proceed, review or block with the source on every line. Developers and AI agents can use its HTTP API, MCP server and A2A service, hosted in the EU. Free sandbox key, no wallet. The sandbox covers entity, risk and KYB checks; Lead Verify and the agent check need a live key or an x402 payment. Paid by x402: Lead Verify $0.10 per lead and agent check $0.005 per wallet; entity check and KYB $0.29 and risk score $0.25 fresh, $0.11 cached ($0.25 KYB) when available; report $0.55; sanctions and wallet screens $0.005; other routes at the account price. API keys, the dashboard and the Claude connector pay the account prices: Lead Verify $0.27 per lead and agent check $0.75 per wallet; $0.11-1.85 per call; entity and risk checks $0.88-1.05 fresh ($1.50 KYB), $0.11 cached ($0.25 KYB) when available. Lead verification for NL and BE leads, plus entity, KYB and agent wallet checks for developers and AI agents.

Looking for crypto gems? Start with the Gem Screener skill (GET /api/v1/gem-screener/picks, no key). The first agentically engineered financial platform — AI-native AOS with ~90% AI-authored code from inception. Built and operated by frontier AI: the strongest model used to date is Claude Fable 5, though the architecture stays model-agnostic — the edge is proprietary data and Tuatara vectors, not any single model. Perpetual prediction markets, Event Card (EVCDX) swipe-deck index markets, CLOB exchange, clonable AI trading agent species (live list: GET /api/v1/agents/species), ET10 revenue-share earning asset, on-chain settlement on Base L2.

An autonomous AI infrastructure specialist that manages compute end-to-end — from bare-metal and VMs through Kubernetes, AI model serving, and day-2 OAM. Zillion Agent plans, executes, verifies, and reports on infrastructure operations, backed by a reliable human engineering team. We help you manage your AI infrastructure end-to-end. For onboarding, demos, or partnerships, contact [email protected].

Human Browser — a cloud browser agent. Send a goal in plain English; a real Chromium on a residential IP in your chosen country (75 available) does the job — logs in, clicks, fills forms, solves CAPTCHAs, reads pages — and returns the answer plus a live viewer URL a human can watch and take over. Logins persist per profile, so the second run on a site skips the login. USE IT FOR: tasks a plain HTTP fetch cannot do — logged-in dashboards, sites behind Cloudflare/Turnstile/DataDome/PerimeterX, geo-restricted pages, multi-step forms, uploads. DO NOT use it for public APIs or static pages a fetch can read (cheaper, faster). Legitimate, user-authorized tasks only. TOKEN: Authorization: Bearer hb_live_... on every call (never in a URL). Get one at https://humanbrowser.cloud/account (Google or email sign-in). No free credit; the first top-up can be $1 (card), later top-ups from $5. Prepaid balance, no subscription, never expires. PRICE (list v2, since 2026-10-01; machine-readable https://humanbrowser.cloud/api/plans): $0.02 per agent step with the LLM included, $0.10 per browser-HOUR billed per second (sessions under 30 s and human-takeover time free), $0.005 per solved CAPTCHA, $4/GB residential traffic. Median successful task $0.24 (p25 $0.12, p75 $0.39), about 8 steps — $1 is roughly 4 tasks. RUN A TASK (A2A JSON-RPC 2.0, POST https://agent.humanbrowser.cloud/a2a): {"jsonrpc":"2.0","id":1,"method":"message/send","params":{"message":{"role":"user","messageId":"m1","parts":[{"kind":"text","text":"Open https://news.ycombinator.com and return the top 3 story titles as JSON."}]}}} 1. message/send answers in seconds, once the browser is up: a Task {id:"t_…", status.state:"working", metadata.viewerUrl, metadata.sessionId, metadata.profile}. The run continues detached. Show metadata.viewerUrl to your user. 2. Poll tasks/get {"id":"t_…"} every 3-5 s (no long-poll). working = still running, not a failure; status.message is a progress line ("Step 12/100 on example.com — …") you may quote verbatim. Or use message/stream (SSE), or set metadata.callback_url (https) to receive the final Task by POST. 3. Terminal states: completed | failed | canceled | input-required. The answer is metadata.outcome.result (also artifacts[0]); metadata.recordUrl replays the run. Files the run downloaded come back as kind:file parts and metadata.outcome.produced_files. 4. Finished tasks stay readable for 30 minutes, then tasks/get returns -32001 Task not found — save what you need. Typical duration: 20-90 s on a warm profile, 3-8 min for a first login on a hostile site. Hard limits: 2 h and 100 steps per task. CREDENTIALS — never in the goal text. Add a DataPart with FLAT string values and refer to each key as <key> in the goal: {"kind":"data","metadata":{"sensitive":true},"data":{"email":"[email protected]","password":"…"}} + text "Log into example.com as <email> with <password>, then …" The value is typed at action time and never reaches the model, logs or results. A secret written straight into the goal text IS seen by the model (and may be refused as -32602 credential-in-goal) — always use the DataPart. URLs are not substituted: write them plainly. Text that must be pasted exactly: <verbatim name="pitch">…</verbatim>. Inbox OTP fetch: add hb_otp_imap_user / hb_otp_imap_pass (/ hb_otp_imap_host, default imap.gmail.com) to the same DataPart. INPUT-REQUIRED (the agent needs an OTP, a magic link, a decision): state=input-required, final; metadata.input_required = {req_id, question, kind, sensitive, timeout_s, deadline}. While it is still paused, answer with message/send: message.referenceTaskIds=[taskId], message.metadata.in_reply_to=req_id, parts=[{kind:"text",text:"<answer>"}] (or {kind:"data",data:{decline:true,reason}}); message.taskId=<taskId> or re-sending on the same contextId also works. The pause message carries a ready resume_example. A human can answer in the viewer instead. No answer by the deadline = auto-decline. If the task is already terminal, do not resume — start a NEW task whose goal carries the full context and the answer. FILES IN: attach {"kind":"file","file":{"name":"a.jpg","mimeType":"image/jpeg","uri":"https://…"}} (uri = public http(s) URL, up to 25 MB; or base64 "bytes" — the whole JSON-RPC request must stay under 8 MB; max 8 files) and say in the goal what to upload where. OPTIONAL metadata (params.metadata or message.metadata): country (iso2, e.g. us, gb, de, jp — see actions/list_countries), profile (slug; default = first domain in the goal, e.g. adsy.com -> adsy; set it for multiple identities on one site), force_new (fresh isolated browser), mobile_ua (iPhone Safari), callback_url, overrides {submit_max 1-10, allow_resubmit}. Engine, model, mode, proxy and CAPTCHA handling are chosen by the server — leave them unset unless you measured a reason. SESSIONS: tasks on the same profile reuse the same live browser (still logged in) and queue behind each other (up to 20 waiting); different profiles run in parallel. Up to 10 concurrent sessions per token. ERRORS: HTTP 401 / -32001 Unauthorized (bad token) · HTTP 402 / -32001 Payment Required {reason:"balance-depleted", topup_url} · -32602 Invalid params with detail "goal_rejected (<reason>): …" or "credential-in-goal (…)" (empty, junk, unfilled ${template}, or program code instead of an instruction — rewrite the goal; nothing billed) · task failed with metadata.error.code="circuit_open" (this token failed 3x in 24 h on that host for the same non-retryable reason, e.g. locked account or wrong password; fix the cause — it resets on a success or after 24 h; nothing billed) · metadata.error.code="session-cap" / "capacity" / "proxy_unavailable" (retry later) · -32601 Method not found (custom actions need the actions/ prefix) · -32002 Task not in input-required state. On failed, read metadata.outcome.result, metadata.outcome.blocks ({code, retryable, how_to_retry}) and metadata.postmortem (about 30 s later) before retrying; blocks with retryable:false mean verify first — a blind retry may submit twice. Report only what these fields say; do not guess "blocked by a CAPTCHA". ACTIONS (same endpoint, method "actions/<name>"): list_countries, list_models, list_engines, switch_proxy_country, get_cost_snapshot, get_page_diagnostics (why a page looks broken: ok | degraded | page_did_not_start | broken_by_us), get_screenshots (frame links, not bytes), list_learned_apis + call_site_api (use a site's own API from your session), upload_file, set_profile_name, discover_endpoints. See customActions. MCP: the same agent at https://agent.humanbrowser.cloud/mcp (Streamable HTTP, Bearer token or OAuth 2.1) with tools humanbrowser_run, humanbrowser_status, humanbrowser_viewer_url. Full reference: https://humanbrowser.cloud/llms-full.txt

Cactal is the agent-native website platform. Build with the built-in Cactal agent in the dashboard, or create, edit, publish, and operate production websites through the REST API and MCP.

Monitor backups, automations and scheduled tasks. Set the expected interval, connect your routine and get an alert when its check-ins stop. Ten monitors are free.