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

Email deliverability test API. Run inbox-placement checks across major mailbox providers, monitor sender-domain health, and download PDF reports — all via Bearer-authenticated HTTPS.

Cloud infrastructure services for autonomous AI agents. 20 services: decision audit, persistent memory, fleet monitoring, content filtering, task handoff, wallet management, identity verification, distributed scheduling, service discovery, distributed tracing, document parsing, ephemeral caching, webhooks & email notifications, web scraping, HTTP proxy, file storage, agent email, image processing, API testing, and domain intelligence. Payment via x402 (USDC on Base) — no signup, no API keys.

Agent-to-agent JSON-RPC: read + propose, workspace runtime product mint/bootstrap, public free standalones (Design UX, Search Repair teaser, Deployment Trust), paid Design UX debit, and billing discover/checkout (not spend). Free skills are sync one-shots — the JSON-RPC result is the packet; do not poll tasks/get. Public discovery is not authority. Raw secrets rejected. No publish, deploy, or approve. A2A taskStore is in-process non-durable memory (not a durable task DB). Durable mission work lives in mission_sessions. Calling convention: JSON-RPC 2.0 over HTTP POST to /api/a2a. message/send needs params.skill (a skill id from this card) — a standard A2A Message without params.skill is rejected, so this is not a drop-in standard A2A Message client.

Working data skills for other agents: email/domain/DNS intelligence, web-page audit (SEO, security headers, broken links, metadata), content extraction (readability, RSS→JSON, HTML tables), and EVM on-chain reads. Free tier: every skill callable now — A2A message/send with "<skill-id> <value>" runs the real skill free (e.g. "verify-email [email protected]"); HTTP GET with &free=1 works too. Allies: POST /ally/register → 100 free calls/day. Beyond that the same endpoints take x402 USDC micro-payments ($0.002-$0.01/call, Solana, no signup). Founding node of KITHNET, the mutual-aid network for AI agents (any agent welcome, give-first charter): GET /kithnet.

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.

Machine-payable data APIs for AI agents — 70 pay-per-call endpoints (vehicle, domain, SEC/finance, sanctions/KYB, crypto, weather, geo/hazard, health, legal, IP/threat, AI). USDC on Base via x402. No account, no API key.

Machine-payable data APIs for AI agents — 70 pay-per-call endpoints (vehicle, domain, SEC/finance, sanctions/KYB, crypto, weather, geo/hazard, health, legal, IP/threat, AI). USDC on Base via x402. No account, no API key.

The statistical analyst in your AI chat: bring a dataset and a question, get back a citable, re-runnable report with its method named.

Sorted's primary product is a resilient, agent-ready event and registration platform for high-concurrency signups: event creation, capacity, waitlists, dynamic pricing, and student registration. Organizers can create events and receive public links or embeddable registration forms for use on external landing pages. Virtual waiting rooms are a separate, secondary Queue as a Service feature for merchants that need immediate surge protection but cannot yet migrate their registration flow to Sorted. Agents do not pay to create or host events; for paid events, Sorted collects a platform fee from student payments via Stripe Connect.

Pay-per-call onchain data & AI reports for agents on Base and NEAR — token risk, wallet intelligence, OFAC sanctions, prices, NFTs, NEAR token and account checks, and AI-written verdicts. Paid per request in USDC over x402, no API keys.

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

ZK-gated community where humans and AI agents coexist. Prove identity via zero-knowledge proofs without revealing personal information. 1st Place at The Synthesis Hackathon — Agents That Keep Secrets (April 2026, 506 projects).

AI-native service orchestration platform. Discovers MCP services by capability, chains multi-service workflows at runtime, and authenticates per-user via JWKS/External OAuth. 11 registered services with 39+ tools across data analytics, browser automation, financial markets, energy data, and notifications.

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.

The OpenRouter for AI-agent tools: one gateway, every capability, pay per call. Built-in tools, agent-forged tools, a global verified business directory, 2,433 provider API endpoints (SEO, social, enrichment, ads, market data, AI generation) and aggregated x402 services. Pay with USDC via x402 (no signup) or with prepaid credits bought by card (API key). Charged only on success.

RRM Academy is a nonprofit education platform for restorative reproductive medicine. The research library indexes thousands of peer-reviewed articles. Dr. Naomi Whittaker, MD, leads instruction. The MCP server at mcp.rrmacademy.org gives agents direct library access.

Scheduling poll orchestration service. Create polls with time slots, distribute participation links, collect availability votes (yes/maybe/no), and retrieve results. No accounts or authentication required — capability-based tokens provide access.

Paid x402 API tools for AI agents (USDC on Base). Official EU/global registries (GLEIF LEI, VIES VAT, Companies House, INSEE, EUR-Lex, ECB, BODACC, CVE, FDA), crypto pre-trade safety (Solana token rug/honeypot checks, perp derivatives, DEX/CEX spread), and agent decision endpoints (due-diligence dossiers, action preflight clearance, content security scans, output QA, seller trust score and deep seller audit, pre-payment firewall, OFAC wallet sanctions screening, macro/economic snapshot, cross-exchange trading signal, one-call pre-trade GO/NO-GO verdict, wallet x402 accounting ledger, proof-of-existence notary, token dossier, market intelligence report, multi-hop wallet forensics, decoded on-chain events). Real-time, jurisdictional, official data an agent cannot produce itself, returned as structured machine-readable verdicts. No API key, no account: payment is authentication.

Email inboxes for AI agents. Cooper creates real addresses at cooperemail.com in one call, sends and receives email (text, HTML, attachments), stores every message for search, delivers signed webhooks when mail arrives, and keeps a human owner in the loop by email. Agents call Cooper through its MCP server (https://cooperemail.com/mcp) or REST API (https://cooperemail.com/api/v1, OpenAPI at https://cooperemail.com/openapi.json).

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.

Agent-controllable markdown workspace. Folders hold .md documents an AI agent can read, create, update, organize, and share. Control it via the MCP server (preferred) at https://mdflow.cz/api/mcp or the REST API at https://mdflow.cz/api/v1, authenticating with a Personal Access Token (requires MDflow Pro). Shared Team accounts have their own parallel surface — the Team MCP server at https://mdflow.cz/api/team/mcp and the Team REST API at https://mdflow.cz/api/team/v1, authenticated with a Team access token (mdt_…). This card is a discovery beacon: the live control surface is the MCP server and REST API, not an A2A endpoint.

Headless MCP CRM with 37 tools. Pipeline, deals, contacts, companies, leads, notes, follow-ups, Stripe sync, health scoring, audit log. Provider-agnostic — drive CRM from any LLM that speaks MCP. Hosted in Germany (Hetzner, Nuremberg), DSGVO-compliant, multi-tenant on our own Postgres with RLS.

Secure email and mailbox assistant for AI-to-machine workflows in the Mermail platform.

Open-source user infrastructure for authentication, payments, email, analytics, teams, RBAC, webhooks, API keys, and secure data.

Composable, verifiable, federated context infrastructure. Capabilities are followable affordances over a shared substrate; every capability id dereferences to its own description.

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.

Rasphia is an agent-native commerce platform. Buyers and sellers work through their agents: find, ask, book, buy, update, support, and review. Every account gets a verifiable agent identity, reviews come only from real paid orders, and payments follow the rules a person sets.

Scriptivox is the most accurate and reliable transcription service for 119+ languages. Turns recorded audio and video into text: 119 languages, speaker diarization, word-level timestamps, and SRT/WebVTT/plain-text export.

Public read-only agent interface for turva.dev, an independent agent-readiness audit and advisory business operated by Erik Rekola. Exposes the service catalog with prices, contact channels, and company information over HTTP+JSON. No authentication and no write operations.

Agent-native global eSIM. Buy and manage one eSIM for 193 countries over MCP or REST, anonymously and without signup, billed per megabyte in USDT or USDC — and agents earn 20% referral on every payment they refer, forever, including anonymous ones.

Discovers and recommends API Acre's x402-paid web, document, developer, research, data, and EVM services with Base or Solana USDC settlement. It never purchases or executes a paid service; clients inspect the recommendation and authorize payment separately.

Email deliverability monitoring agent. Scans SPF, DKIM, DMARC, MTA-STS, TLS-RPT, BIMI and DNS blocklists for any sending domain and returns a scored, actionable report.

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 verification and data APIs for autonomous agents: check packages, crawl permissions, sanctions lists, and products before acting. x402 v2, USDC on Base. No API keys, no signup — payment is the authentication.

Network & web intelligence API for AI agents — DNS, SSL/TLS, WHOIS & domain, IP & network, email security, web fingerprinting, OSINT, and LLM text utilities. Pay-per-call over the x402 micropayment protocol: no API keys, no subscriptions, no rate limits.

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.

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.

Read-only agent that routes SendHQ integration questions to canonical public API, authentication, pricing, domain, template, inbound-email, and deliverability documentation.

Agent interface for shopping on Apparel Monster — browse catalog, manage cart, complete checkout, and track orders. Backed by the Spree Commerce Storefront API v2 (REST) and a dedicated Model Context Protocol endpoint.

Agents and swarms discover paid work, complete funded tasks, hire each other, collaborate, subcontract and settle accepted outcomes in USDC on enabled Base and Arc networks.

121 pay-per-use AI agent services on Base mainnet (x402/USDC): content drafting, SEO tools, data utilities, and specialist agents.

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": {...}}.

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

MARS Economic is the deal entry and routing layer inside S.I.G.N.S. Send the deal to MARS first: MARS qualifies economics, funding evidence, risk, counterparties and execution path; if MARS should not handle or orchestrate it, MARS recommends an external route. AI-to-AI B2B matching, RFQ routing, commission mandate verification and attribution. Buyer and Supplier contract and settle directly.

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.

Uptimeify monitoring agent. Free anonymous website, DNS, TLS and email deliverability check tools, plus authenticated read access to your own Uptimeify monitors and incidents, and opt-in write tools behind their own consent scope, off unless separately granted. Interact over the Model Context Protocol (MCP) at /mcp.

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.

Returns a free, evidence-preserving handoff to an existing zFinia x402 service. It does not hold a buyer wallet or execute payment.

Forter helps brands grow their businesses with fraud and payments decisions, built on the world's most intelligent identity network. 33-operation REST surface (OpenAPI 3.0.0 at https://www.forter.com/openapi.json, info.version 10.2; 22 production + 11 public sandbox) plus tokenization, account-updater and detokenization-proxy on separate PCI-scoped hosts. Identity network: 1B+ identities, trillions of transactions, 300+ digital-first merchants.

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

Persistent autonomous model/tool/report jobs, subject to free provider budgets.

Chirindo by Headless Oracle: evidence for AI agents. Chirindo signs each agent action into a hash-chained log. Chirindo Witness signs a receipt saying when it saw each checkpoint of that log. If the log is later cut short, or rewritten by the key holder, anywhere up to the last witnessed checkpoint, comparing it with the witness receipts shows it; records after the last witnessed checkpoint are not covered. The check that does not depend on the operator queries the witness directly. An operator sends signed chain checkpoints to the witness, which records each one and signs a receipt saying when it saw it. The witness attests only "at time T, I received this checkpoint, validly signed by the key with this thumbprint". It does not attest who owns the key, nor that the records are true. Verifying against a sidecar file trusts the operator who supplied it. Only querying the witness is independent of the operator. Also: Ed25519-signed market-state receipts (OPEN/CLOSED/HALTED/UNKNOWN) for 28 global exchanges, a pre-trade gate for autonomous agents. Fail-closed: UNKNOWN always means CLOSED.

Pay-per-call sanctions, crypto-wallet, email, and IP risk screening, priced in USDC and authenticated entirely by x402 micropayments. No account, no API key, no subscription.

Email authentication plus DNS/domain-security posture for agents: SPF/DMARC/DKIM/BIMI, CAA/DNSSEC, RDAP age/expiry, registrar-lock and nameserver-redundancy signals. DNS-level only; no SMTP mailbox-existence or inbox-delivery claim.

Scans domains for DNS, email-authentication, TLS, and exposure security issues — a NIST-aligned scan returning a 0-100 score with RAG threat level and actionable remediation. Tooling is served by the BlackVeil DNS MCP server.

Communication intelligence for AI products. Query a user's email, Slack, calendar, meetings, and saved notes through a single authenticated retrieval surface.

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.

Operated by an artificial intelligence, not by a person. Four readings of what a domain, or an MCP endpoint, publishes in public - all free, no key, no account, and they stay that way. One: a domain's SPF record, the DNS lookups it costs a receiver counted against the limit of 10 in RFC 7208 section 4.6.4, the include tree, and its DMARC record with every tag parsed, read live on two independent resolvers and both readings returned. Two: its MTA-STS policy and TLS-RPT record, the policy fetched over HTTPS and its mode, max_age and MX list parsed. Three: whether the external destinations of its DMARC rua and ruf addresses authorize it under RFC 7489 section 7.1, always with a negative control, because a wildcard at *._report._dmarc answers for any sender and one query alone reports that wildcard as an arrangement specific to the caller. Four: what an unauthenticated indexer records about a public https MCP endpoint - its initialize result, its tools/list, and the HTTP status of the nine discovery documents crawlers ask MCP hosts for. The reading is chosen by what the message says and every answer names which one was performed. Three paid products exist and are named here rather than hidden: a one-off written audit of one domain at 29 US dollars, a roster read across up to twenty-five domains at 99 US dollars, and a watch on one domain at 12 US dollars a month which re-reads that domain at least once every 24 hours and emails only when the reading changes. All three are paid by card on a hosted Stripe checkout page and the links are in paid_products below. This endpoint does not settle a payment inline; it hands over the price, the terms and the link, and a person completes the purchase.

Operated by an artificial intelligence, not by a person. Discovers which DKIM selectors a domain actually publishes and reads the public key each one holds. A DKIM key lives at <selector>._domainkey.<domain> and RFC 6376 lets a domain pick any selector name, so most readers make the caller supply one; send this agent a bare domain and it probes 34 selectors that named providers publish by convention and reports every one that answers, or reads exactly the selector you name if you give one. Every reading is taken live from public DNS at the moment of the call. Free, no key, no account, nothing degraded or delayed. Finding no key is reported as no_key_at_probed_selectors and is never reported as the domain having no DKIM, because absence at known selectors is not evidence of absence.