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

Shopify-first AI marketing platform. Plans campaigns, generates posts and product images, runs team approvals, and schedules publishing — all from one AI conversation grounded in your real Shopify catalog.

ThinAir Data — PostgreSQL, MySQL, and SQL Server in a single MCP session. 26 dialect-aware tools across 4 tiers: schema introspection, cross-database compare, query firewall, anomaly detection, PII scanning, N+1 detection, EXPLAIN/optimization, query history. Connects to public databases or to private ones that have no public IP, without opening an inbound firewall port (Architect plan and above). Read-only enforced at three independent layers (SQL guard, session READ ONLY, optional per-connection custom firewall). OAuth 2.1 + API key auth.

Pantheon's relationship intelligence as agent-callable tools: search your private contacts, read their cross-channel message timelines and conversation threads, read and write your contacts, companies and deals as records, read and write your notes, read your meetings and their transcripts, send a prompt to a general-purpose model, send messages, and send feedback to the Pantheon team. Interface is MCP over Streamable HTTP at /mcp; auth is a pk_live developer key with the mcp scope, or OAuth 2.1 via auth.pantheon.run.

Zenovay is a privacy-first, real-time web analytics platform. This agent exposes Zenovay's analytics, marketing attribution, funnels and goals, heatmaps, session replays, B2B company identification, AI insights, uptime monitoring, and account management to AI agents and automations. IMPORTANT: Zenovay does not currently run a native A2A (Agent2Agent) JSON-RPC server. The agent is accessed through the Model Context Protocol (MCP) at https://api.zenovay.com/mcp (JSON-RPC 2.0 over the Streamable HTTP transport), authenticated with OAuth 2.1 (PKCE / S256; MCP access tokens are prefixed zvt_). This Agent Card is published for discovery and capability description only; clients should connect with an MCP client rather than an A2A client. The MCP server (name: zenovay-analytics, version 1.0.0) currently offers roughly 109 tools. See https://docs.zenovay.com/mcp for connection details.

Meet Kai LLC (Puerto Rico) is a business phone company. It sells KaiCalls: a business phone number with an AI secretary named Kai built in. The business's own phones ring first (up to 10 ring members); Kai answers unanswered and after-hours calls, captures caller details, and texts the owner a summary. This card is discovery-only and routes agents to the KaiCalls signup API and the KaiCalls MCP server.

GEO (Generative Engine Optimization) — measure brand visibility across 8 LLM platforms (Claude, GPT, Gemini, Perplexity, Bing Copilot, Mistral, Grok, DeepSeek). 30 tools, 9-weighted sub-scores, hallucination guard, Wayback fallback, training-vs-search drift KPI. Provider-agnostic, EU Nürnberg.

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.

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

BlogSEO is an AI SEO platform: keyword research, SEO articles written in the brand's voice and published automatically to the website's CMS, backlinks, Google rankings and AI visibility tracking. BlogSEO does not run an A2A JSON-RPC agent. Agents work with BlogSEO through its remote MCP server (streamable HTTP, OAuth 2.1), the only interface listed in supportedInterfaces. Use this card to discover what BlogSEO can do, and the MCP server to do it.

Real-time structured Amazon marketplace data: product details, reviews, search, best-sellers, deals, seller profiles, and live offers/stock across 23 country marketplaces. Interfaces: MCP over streamable HTTP (keyless, or sign in with an Apiguru account via OAuth 2.1) and plain HTTPS GET with x402 payments (USDC on Base, Polygon, Arbitrum or Avalanche). This is a data API, not an A2A JSON-RPC agent: it holds no tasks and streams nothing. Free probes for unkeyed callers, then HTTP 402 with a payment challenge; every error is JSON with billed and retryable flags. Discovery: https://agent.apiguru.app/.well-known/x402 lists every endpoint with price and schema.

Buys social media growth for a target profile, post, channel or video: followers, subscribers, members, views, likes, plays and engagement across Instagram, TikTok, YouTube, Telegram, X and more. Searches a priced catalog, recommends an option for a goal and quantity, quotes the exact price server-side, places the order and tracks it to delivery. Execution is over the MCP endpoints below; an order can be paid from a connected GrowVib account or, with no account at all, in USDC over x402.

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.

Agente de subastas judiciales de inmuebles en España (BOE). Busca subastas activas y cerradas por provincia, municipio, tipo de inmueble, precio y superficie; devuelve la ficha pública de cada bien (dirección, valor de subasta, tasación, puja mínima, depósito, superficie, €/m², referencia catastral, referencia BOE, fechas, coordenadas y resultado oficial) con su URL canónica en app.subastech.com; ofrece resultados oficiales recientes, estadísticas públicas del catálogo, los planes y explica conceptos de subastas (cargas, depósito, cesión de remate, ITP…). Con una cuenta de Subastech (OAuth 2.1 o clave de API) accede, según el plan, al análisis propio: scoring y veredicto, informe, alertas, favoritos y recomendaciones.

Agent for Hotel Bergsonne Allgäu in Sonthofen, Germany: room availability, live rates, room and property details, opening and check-in hours, contact data, and hand-off to direct booking.

Онлайн-запис до лікаря у Чернівцях через AI-агента: пошук вільних слотів і бронювання за пацієнта.

Long-term AI memory with bi-temporal knowledge graph. 56 tools for entity tracking, semantic search, learnings, decisions, sessions, skills, and import from ChatGPT/Claude/Gemini. Provider-agnostic; works with any LLM that speaks MCP. Hosted at Hetzner Nuremberg (Germany, EU), with tenant-scoped application queries.

Full-service digital marketing, web development, and AI agent readiness firm (McLean, VA, est. 2012). Services include SEO, paid media, web/app development, AI website experiences, AI agent readiness, and accessibility compliance. Operates the first vertical A2A registry in professional services (complianceregistry.net).

Verified emissions data and the Open Footprint canonical model, for agents. Eighteen read-only tools over MCP (remote Streamable HTTP with OAuth 2.1, or the stdio npm package): natural-language queries over a verified emissions knowledge graph (metered), the Open Footprint model — entities, sectors, O-DEF semantics, sector guardrails (free) — validation of payloads against the model and published guardrails (metered), and approved regulatory compliance policies (paid plans). Credit-billed with machine-readable HTTP 402 semantics; optional vLEI-verified agent identity (GLEIF-rooted Agent Authorization credentials).

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

Verified emissions data and the Open Footprint canonical model, for agents. Eighteen read-only tools over MCP (remote Streamable HTTP with OAuth 2.1, or the stdio npm package): natural-language queries over a verified emissions knowledge graph (metered), the Open Footprint model — entities, sectors…

Scribe is an email signature management platform for Google Workspace and Microsoft 365. Agents can manage signatures, teammates, campaigns, and analytics through the hosted MCP server at https://mcp.scribe-mail.com/mcp (OAuth 2.1 with dynamic client registration) or the REST API at https://api.scr…

AI meeting note taker: records meetings, transcribes them, and produces summaries and action items. This agent is exposed as an MCP server (JSON-RPC 2.0 over Streamable HTTP) at the service URL below; connect with an MCP client and authenticate via OAuth 2.1 (see /.well-known/oauth-authorization-se…