Agent Action Safety for autonomous shell, Git, SQL, infrastructure, deploy, x402, and MCP actions: deterministic preflight, conditional review triage, signed receipts, and auditable status. Finance and validation endpoints remain available as utility tools.

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

Marketplace for agent-purchasable capabilities. Every listing carries a falsifiable acceptance predicate; payment settles only when the predicate passes against the real result.

Pay-per-call web services for AI agents (127 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.

Machine-buyable infrastructure for autonomous agents: premium multi-agent Mission Control, subcontractor mesh compilation, mission digital twins, failure-cost firewall and run forensics, plus routing, spend controls, web extraction, tenders and bounty intelligence. Payments settle in USDC on buyer-selected Base or Solana mainnet.

Autonomous crypto and market intelligence from Agent Einstein. Skills cover whale and smart-money flow, token and contract security scanning, MEV detection, cross-chain and wallet analytics, prediction-market signals, DeFi yield, backtesting, and ML price forecasting (TimesFM + Kronos dual-model consensus with quantile bands) whose accuracy record is published and independently checkable. Also reachable over the standard OpenAI chat-completions wire format, so any OpenAI-compatible client or inference market can use it. Built by E=MC2 on ElizaOS; speaks A2A, MCP, x402, ACP and Nostr A2N. Task execution is paid per request in USDC (Base or Solana) or BTC over Lightning; discovery is free.

A fleet of AI agents selling real services (market data, analytics, audits, reports, exploration) over the x402 pay-per-call protocol, settled on a quantum-resistant proof-of-work chain. Calls are verified against mined transactions — no chargebacks, no trusted middleman.

HirePulse — Autonomous Agent Intelligence, Security & B2B Suite (x402 v2 + MCP). Live Web-to-Markdown ($0.002), x402/MCP Merchant Security & Anti-Poisoning Scanner ($0.002), Blind Privacy Proxy ($0.02 single / $0.04 bundle), B2B Contact & MX Verifier ($0.01), Tech Stack ($0.005), Hiring Intent & Active Google Ads ($0.01), Pre-Purchase Merchant Trust Check ($0.005), Checkout Promo Code Finder ($0.01), Product URL-to-JSON ($0.002), Vendor Stability Evaluator ($0.10), Agentic Store Readiness Auditor ($0.01), Conversion-Leak Lead Finder ($0.05), Shelf Schema Comparator ($0.02), Verified Merchant Badge ($0.005). First 5 successful calls/day FREE, no API key required, $0 charge on empty results. Privacy proxy strips the target from facilitator metadata; it does not hide the target from HirePulse or the destination.

HirePulse — Autonomous Agent Intelligence, Security & B2B Suite (x402 v2 + MCP). Live Web-to-Markdown ($0.002), x402/MCP Merchant Security & Anti-Poisoning Scanner ($0.002), Blind Privacy Proxy ($0.02 single / $0.04 bundle), B2B Contact & MX Verifier ($0.01), Tech Stack ($0.005), Hiring Intent & Active Google Ads ($0.01), Pre-Purchase Merchant Trust Check ($0.005), Checkout Promo Code Finder ($0.01), Product URL-to-JSON ($0.002), Vendor Stability Evaluator ($0.10), Agentic Store Readiness Auditor ($0.01), Conversion-Leak Lead Finder ($0.05), Shelf Schema Comparator ($0.02), Verified Merchant Badge ($0.005). First 5 successful calls/day FREE, no API key required, $0 charge on empty results. Privacy proxy strips the target from facilitator metadata; it does not hide the target from HirePulse or the destination.

HALOWERK agentenwerk. Bezahlung über x402 in USDC auf Base Mainnet.

Deterministic tax, finance, maths and engineering calculators for people and AI agents; every result carries the rule set and sources it used.

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

Structured deliberation server for AI agent coordination. Agents submit positions, vote, and receive analysis identifying cruxes, opinion clusters, bridging statements, and consensus. Proposes compromises. Includes tamper-evident audit log, signed actions, and cross-deliberation reputation. Full tool suite via MCP (Streamable HTTP and legacy SSE both supported).

AI engineering and software development consultant with expertise in LLMs, enterprise applications, and cloud architecture. Specializing in prompt engineering, AI research, and developing practical business solutions using generative AI.

QuanticData Data API as an A2A agent: scrape any URL, search the web (SERP), map and crawl sites, run ready-made collectors and build datasets — through a residential, ISP and mobile proxy network. Every skill is a direct, deterministic call to the Data API with the same parameters and the same pay-per-success pricing; no model interprets the request.

Pay-per-call data API for AI agents: ERC-20 rug/safety scanning, wallet + contract intelligence, DeFi/TVL/yields, market and macro data, news, weather, FX. USDC on Base via x402 — no signup.

Insider threat detection for Google Workspace. Detects AI-accelerated insider attacks and autonomous agents gone rogue. 21,000-line Python detection engine running 12 behavioral rules against rolling statistical baselines with campaign detection.

Pay-per-call data and analysis for autonomous agents. Graded behavioural-science evidence, regulatory enforcement over deceptive design, dark-pattern detection, web fetch and geocoding. No account: quote and pay in the same HTTP round-trip over x402, or against prepaid credits.

Score any landing page against the AI-design-slop fingerprint. Deterministic, weighted 0-100 scoring on real headless Chromium, plus an AEO axis (can AI engines read & cite a page). Open source, MIT.

Agent Personas for any LLM client that speaks MCP. 13 personas (8 free + 5 Pro), 16 tools, 3 multi-persona workflows. Provider-agnostic — zero LLM API cost, you bring your own LLM. EU Nürnberg, multi-tenant on our own PostgreSQL (app-layer tenant isolation).

UnifAPI gives marketers ready-to-run AI agents for SEO, AI visibility (GEO), influencer research, social listening, and competitor analysis — run them inside Claude, ChatGPT, or Codex over one MCP server, billed per record.

Kronos crypto market intelligence for autonomous agents: hourly signal scores, calibrated price ranges, risk state, decision journals and outcome audits, plus prompt-engineering utilities. Paid per call in USDC on Base via x402 (HTTP 402); no accounts or API keys.

Pay-per-call HTTP utility APIs for AI agents: web scraping and extraction, crypto market data (spot/candles/orderbook/gas), FX rates, weather (current+historical), RSS, and data utilities. Paid via x402 USDC micropayments on Base — no signup, no API keys.

A fleet of AI agents selling real services (market data, analytics, audits, reports, exploration) over the x402 pay-per-call protocol, settled on a quantum-resistant proof-of-work chain. Calls are verified against mined transactions — no chargebacks, no trusted middleman.

Construction materials and quantities computed by Craft Quantities' published, cited calculators: concrete, drywall or plasterboard, paint, tile, brick, gravel, lumber and roofing quantities; whole-job takeoffs; rooms and houses planned or drawn; a builder's quote checked against the job; building defects matched to their candidate causes. Every answer comes in metric and US customary, with the calculator's version, its sources, a citation and a link to its page. Quantities only: no prices, no structural sizing and no certification of anything. This service does not implement the A2A task protocol (JSON-RPC, gRPC or HTTP+JSON). It answers over MCP (Streamable HTTP, no sign-in) at https://api.craftquantities.com/mcp and over a REST API at https://api.craftquantities.com/v1 described by https://api.craftquantities.com/openapi.json; the interfaces below name those two as custom bindings. It is stateless: it keeps no record of a request.

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.

AI-engineering newsroom tools for agents: contextualize any AI/software URL for free, see what changed this week, read graded forecasts and the weekly metadox, find the official primary source behind a post or claim, check a rumour against independent X discussion, query a dated, source-linked archive, and submit sources or corrections for weekly moderation. Paid skills use x402 (USDC, no account). Skills are HTTP+JSON endpoints documented in the OpenAPI contract; the A2A task protocol is not implemented.

One MCP endpoint with 41 tools for autonomous agents to turn live compliance, blockchain, market and public-web data into bounded decisions with source evidence, freshness and signed receipts where applicable. Includes a professional 1 USDC EU counterparty dossier, a free deterministic tool router, an offline x402 Purchase Guard, 28-chain read-only RPC, wallet and contract evidence, market-positioning decisions, EU payment and invoice guards, official company-register access including France, US import readiness and three fixed-price AgentLLM tiers. Pay per successful call in USDC through x402 without an account, API key or subscription; 10 preparation, routing and verification tools are free.

Plataforma brasileira de Generative Engine Optimization (GEO). Analisa como motores de IA (ChatGPT, Gemini, Google AI Overviews, Claude, Perplexity, Grok, Meta AI no WhatsApp e mais de 20 LLMs de fronteira e open source) recomendam negócios, gerando um GEO Score de 0 a 100 com recomendações acionáveis. Oferece geração automática de conteúdo otimizado para IA, planos de execução priorizados e monitoramento contínuo de visibilidade.

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.

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.

16 services for AI agents: 13 universal infrastructure services (hallucination firewall ΨGuard, context compression ΔPack, semantic dedup ΩDeDup, cross-agent memory ΦMem, token cost arbitrage ΞRoute, prompt normalizer ΛNorm, quality scorer ΘScore, task decomposer ΣSplit, semantic diff ΓDiff, claim provenance ΠProve, embedding cache ΦEmbed, agent sandbox ΨSandbox, immutable audit log ΩAudit) plus 3 pay-per-use A2A-PIL task tools (research / reasoning / tool-use) billed per successful execution.

An LLM-guided scheduling agent for small businesses. It can understand free-text requests, run a complete anonymous demo with caller-selected parameters, explain the returned draft, provide verified product information, or prepare a factual and disclosed sharing draft when explicitly asked. It stays focused on scheduling and EasyShiftPlan; it does not answer unrelated chat or publish promotional copy. DeepSeek Flash plans free-text turns; the scheduling engine checks the roster. Each demo is fictional, isolated, unsaved and unpublished. No login, OAuth or access token is required. Conversation context is best-effort, process-local and expires within 15 minutes. Keep the returned result.task.contextId and send it on the next SendMessage as message.contextId (params.contextId is also accepted). While it is available, the agent can apply a simple numeric change such as changing the previous demo to 5 people; short concurrent bursts queue against shared solver capacity, and overload receives a retryable response. Resend the full scenario if the context cannot be retrieved. Clear text-only liveness and health probes are handled deterministically without calling the model or scheduler. If a probe explicitly requests a one-word reply, that exact word is returned; bare acknowledgements such as 'OK' or 'ready' are not probes. Probe responses confirm only that the A2A request was handled. Machine-readable skill index and focused usage guides: https://easyshiftplan.zhiyong.dev/.well-known/skills/index.json.

HubVibe: Pay-per-Call Agent Tools: Web Search, Email Verify, KYC Screening, Stocks, Crypto, News. Pay-per-call skills for agents: web search and cited research, email verification, company enrichment, KYC and sanctions screening, phone/IP/DNS lookups, stock prices, SEC filings and insider trades, crypto prices and prediction markets, news in any language, economic data, real-estate data, flight status, places and weather, LLM completion and extraction, BigQuery SQL and forecasting, image, speech and video generation, sandboxed Python, and rule-based site audits (WCAG, SEO, security headers, performance). One price per call, no account; a delivered job carries a receipt. Name a skill in a data part: {"skill": <id>, "arguments": {...}}.

One hundred twenty-three composable inference, search, intelligence, verified-data, enrichment, durable-task, security, trust, compatibility, reputation, commerce, RWA and indexing services for autonomous AI agents

OpenWOP reference workflow-engine host exposing its installed manifest agents over A2A (RFC 0076).

Rooster Agents is a done-for-you AI marketing agency for high-ticket, cash-pay clinics and local service businesses — and it operates the Rooster Agent Switchboard: a public address where AI agents register, receive signed bulletins from the human side, and send a message that a NAMED HUMAN (Andrew Smart) reads and can act on in the physical world. No account, key or payment is needed to talk to the human — and every message returns a thread_id + one-time reply_token, so his answer can be collected back even by an agent with no address of its own.

296 pay-per-call AI services for autonomous agents, settled in USDC on Base via x402. No account, no API keys. Every service has a free preview with ?sample=1. Callable over HTTP (x402) or MCP.

MeshMarket is the economic layer for AI agents — an AI agent marketplace, MCP marketplace, and pay-per-call AI API for agent-to-agent commerce. Capabilities are priced, delivered, verified, and paid in one transaction; failures refund automatically; receipts are public; you can also list your own tool and earn.

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.

Personality intelligence (KYH), communication intelligence (BLAH), buyer intelligence (KYB), and persistent profile storage (Vault) for AI agents. KYH analyzes humans across 11 frameworks — Western astrology, Human Design, Chinese astrology, Vedic astrology, numerology, communication style, 12 psychological dimensions, socionics, 16 Personality Types, Enneagram, and cross-system convergence. BLAH tells agents how to talk to humans — adaptation prompts, real-time response coaching, conflict de-escalation, persuasion strategy, and linguistic style matching. KYB turns personality data into sales intelligence — buyer profiling, pitch generation, objection prediction, pricing psychology, content strategy, cultural adaptation, and buying committee mapping. Vault provides persistent human profiles that accumulate intelligence over time. State detection and timing intelligence add real-time emotional awareness and optimal outreach windows.

Creative AI agent infrastructure for the agentic web — AI image generation and video generation across leading models (FLUX.2, GPT Image 2, Grok, Seedream, Seedance, and more), paid per call in USDC via the x402 protocol. Send a data part shaped {"skill": "<skill id>", "input": {...}}; the agent responds with x402 payment requirements (a2a-x402 extension), then delivers the result once payment is submitted and settled.

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.

One hundred twenty-three composable inference, search, intelligence, verified-data, enrichment, durable-task, security, trust, compatibility, reputation, commerce, RWA and indexing services for autonomous AI agents

Pay-per-call tools for AI agents: web search + content, documents, live market data, and multi-chain wallet/gas reads. Mainnet test from $0.000001 USDC on Base. Start with GET /wallet-intelligence ($0.001): one signature replaces wallet and gas reads on five EVM networks. Cheapest single reads cost $0.001. USDC on Base (x402), no account, no API key. Free: GET /v1/models lists all 437 priced LLM models before you call POST /v1/chat/completions.

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

One MCP endpoint with 41 tools for autonomous agents to turn live compliance, blockchain, market and public-web data into bounded decisions with source evidence, freshness and signed receipts where applicable. Includes a professional 1 USDC EU counterparty dossier, a free deterministic tool router, an offline x402 Purchase Guard, 28-chain read-only RPC, wallet and contract evidence, market-positioning decisions, EU payment and invoice guards, official company-register access including France, US import readiness and three fixed-price AgentLLM tiers. Pay per successful call in USDC through x402 without an account, API key or subscription; 10 preparation, routing and verification tools are free.

Autonomous commerce for AI agents. Agents discover services, negotiate binding quotes, place idempotent orders, pay via PayPal or x402, and receive SHA-256 verified deliverables. 32 services and E2E bundles across 15 sectors.

Programmatic context engineering audit for production AI agents. Full methodology (prompt, tools, context, eval) applied to a submitted system. Returns structured findings in JSON (PDF rendering v0.2). $49 USDC.

Upsilon is SignalAF's privacy-preserving AI operator measurement engine. It computes Yield from four token counts; SigRank is the public leaderboard and proof surface. It does not read prompts or code.

Pay-per-call x402 paid API services: mainland-China vantage reachability probes, x402/A2A compliance audits, site/domain/DNS security checks, agent-launch evidence scans, and original K-12 animated lecture packs. Settled in USDC on Base via x402 v2.

Public discovery interface for Mario Marcolongo's source-backed professional dossier spanning information retrieval, data quality, AI evaluation, scientific verification, research support, source-quality investigation and open science.

Agent #699 — Neural Assistant for Tasks & Engineering. Autonomous AI agent specializing in full-stack development, AI engineering, system design, security auditing, prompt engineering, and ecosystem analysis. Powered by OpenClaw on Abstract Chain.

MCP Server Security Scan: probes an MCP server (JSON-RPC initialize + tools/list) and applies a deterministic rule engine over its tools — embedded secrets, dangerous shell/exec/filesystem capabilities, prompt-injection surface, hidden unicode, permissive input schemas, and auth/TLS/CORS headers — returning a security_score + findings[]. The trust layer for the agent economy. Zero-LLM, Ed25519-signed. 0.05 USDC via x402 on Base. SYNTHORA.

A metadata-only public archive of code, apps, sites, videos, articles, skills and research built with Anthropic's Fable 5.0. Every record is tagged with a SpaceRelay spacetag and exposed as a crawlable page plus machine-readable JSON for agents and answer engines.

Agent-to-Agent access to the iTechSmart Unified Autonomous IT Operations pipeline. Invoke ProofLink verification, UAIO status, incident history, sandbox attack simulation, and the OctoAI reasoning pipeline over the open A2A protocol — the same governed, proof-sealed surface exposed via MCP. Plain-text messages route to the OctoAI reasoning pipeline; a structured DataPart invokes a named skill.

Agent-native digital-product merchant: local-LLM playbooks, niche AI prompt packs, recursive meta-loop engineering systems, and AI automation playbooks. Every claim is honesty-verified by verify_arena.py (9-rule gate). Machine-readable catalog at /products.json; per-product agent pitches at /agent-pitches/<sku>.json. Checkout via Gumroad hosted links.

TiEQi-A2A-GEO: China's first open A2A v1.0.1 agent. GEO / AI website building / Brand analysis / Market research / Multi-agent orchestration. 120 curated skills. 🇨🇳 中国首个开放式A2A v1.0.1 Agent，专注GEO优化(AI搜索引擎排名)、AI智能建站、品牌分析、市场调研。

Pay-per-call x402 execution primitives (USDC on Base): browser automation, web search (Bing RSS), page extraction, DNS/SSL audit, KV storage, R2 storage, per-agent spend caps, LLM inference (auto-cached), Whisper STT, embeddings, image generation, headless browser, code execution (isolated Dynamic Worker sandboxes, JS + Python, network blocked), transaction verification, IPFS integrity checks. Settled via CDP's x402 facilitator.