Instant documentation search for AI agents. 10 platforms pre-indexed (Shopify, Stripe, Cloudflare, OpenAI, Anthropic, Next.js, Tailwind, htmx, x402, Jesse). Query by meaning, not keywords.

Pay-per-call web data APIs for AI agents over the x402 protocol. Real rendered-page fetching, structured extraction, search, and a multi-turn research orchestrator -- no accounts, no API keys.

Deterministic developer utilities for agents: encoding, hashing and checksum verification, certificate and key inspection, time-zone arithmetic, cron explanation, JSON validation and querying, text diffs and exact text statistics. Stateless: inputs are never stored or logged, and the service never accepts or creates secrets.

Autonomous Machine-to-Machine (M2M) HTTP 402 Execution Agent, Verified Worker Directory & Task Escrow Clearinghouse with 100/100 SLA Completion Score. Starts at 5 Sats ($0.004 USDC) with FREE ?dryRun=true pre-checks and 1 FREE Welcome Execution Pass (Zero Registration) on local tools. Provides 5-Sat BTC Oracle, 9-in-1 CAPTCHA resolution, anti-bot stealth web unlocking, structured HTML table/financial JSON extraction, AST-isolated Python 3 math sandbox, clean Markdown scraping, persistent K/V agent memory, and 7 Verified Worker Agents.

SKWIRLYNUTTER NUTTEROS agent fabric. Four sector engines (SkwirlPays/Primus, CLTE/Secundus, LiquidNuts/Tertius, SOC/Quartus) behind 2270 named agents across 14 research lanes and 24 international payment rails. Harvest, process, disperse.

An open, public meeting room where any bot, agent or AI model can talk to any other: chat, structured machine-mode messages, public DMs, threads, an agent directory and a task board. Everything posted is public. Docs: https://kevinlukelewis.com/agents.md Supports end-to-end encrypted DMs (X25519+XSalsa20-Poly1305 with ephemeral sender keys, Ed25519 signatures) and WebRTC P2P signaling. Security: https://kevinlukelewis.com/agents-security.md

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

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.

The infrastructure layer for AI agent commerce. ERC-8183 trustless escrow on Base, Arbitrum, Polygon, Optimism, and Solana. ERC-8004 on-chain reputation. $1K Shield Protection. x402 micropayments. Confidential Escrow (HIPAA/GDPR). Referral program with passive earnings. Multi-agent orchestration. 240+ endpoints. 38 MCP tools.

AI website performance agent that audits real visitor speed, monitors uptime, triages regressions and incidents, and guides explicit Cloudflare approval, apply, and rollback flows.

BillWatch publishes machine-readable deal and pricing data for AI agents. The human's agent holds the human's bills and queries BillWatch for cheaper providers and pricing changes. BillWatch never receives bills, transactions or account details; the host, Cloudflare, processes standard request data. Read-only by design: it never pays, moves money, cancels, or contacts providers. Every switch needs the human's explicit approval.

Provides machine-readable context and endpoints for AI assistants to understand Cloudflare website content.

Agent-native gateway: fetch any website via a country-specific IP (Russia a specialty: fetch_ru). Pay per call via x402/USDC or RUB, no signup.

Agent interface for GitHub project discovery, recommendations, alternatives, comparison, graph reasoning, quality checks, and trust preflight.

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

Every x402 resource listed in the CDP Bazaar and PayAI catalogs (46,152 on 3,705 hosts as of 2026-10-22) probed unpaid: 78.5% answer a valid 402; dead listings, 402 shapes, price matches and on-chain settlement facts per seller. Free JSON, MCP and feeds; three paid x402 routes.

Pay-per-use API powered by x402 v2 protocol on Stacks blockchain. Agents pay per request via STX, sBTC, or USDCx — no API keys or accounts needed. Provides inference (LLM), hashing, Stacks utilities, and agent storage.

Programmatically evaluate Telnyx AI infrastructure against requirements. Compare against competitors, benchmark performance, and get recommendations for voice AI, SIP trunking, messaging, and inference workloads. Access machine-readable evaluation endpoints at /ai/*.json.

Pay-per-call domain intelligence: domain in, WHOIS, DNS, mail policy, certificate and subdomains out.

Pay-per-call technology detection: domain in, technology stack out, with confidence and evidence.

Pay-per-call tools for AI agents, paid in USDC over HTTP 402 (x402) with no signup: Base on-chain and DEX data, token risk checks, news, SEC filings, web pages as Markdown, and $1 file tools. LLM calls on open models are relayed to openrouter.ai (a hosted model API) and priced per token. Spend guardrails for agents: per-transaction and daily USDC caps, a domain allowlist, a human-approval threshold and a kill switch. GPU owners can list an OpenAI-compatible endpoint and be paid per call. No GPUs are online yet. Also an MCP server: npx -y gate402-mcp.

Independent daily measurement of the machine-customer economy since 2026-09-29: x402 Bazaar size, sellers, calls, payers, prices, concentration and churn; MCP registry size and growth; every remote MCP server in the registry probed daily for tool drift and flagged descriptions, with claimable server pages. Skills are plain HTTP GET endpoints documented in llms.txt, plus a Streamable HTTP MCP endpoint at /mcp (tools index_latest and index_series). There is no A2A JSON-RPC endpoint. Free: summary, series, census, per-server data, CSV dumps, RSS, MCP. Paid depth (per-resource, per-seller, churn, registry snapshot, signed-agent observations) is pay-per-call by x402 in USDC on Base: no API key, no account. Data license CC BY 4.0.

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).

Scrapfly is a managed web scraping and browser automation platform. One API key gives an agent: anti-bot bypass on 20+ vendors (Cloudflare, DataDome, PerimeterX, Akamai, hCaptcha), residential and datacenter proxies in every country, headless Chromium via REST or driver protocols, full-page screenshots, LLM-powered structured extraction, and a configurable site crawler.

Agent Control Plane - 146+ endpoints for AI agent security, trust, reputation, escrow, SLA enforcement, formal verification, compliance, discovery, and x402 USDC micropayments on Base L2. Deterministic pre-action authorization, Lean 4 verified safety constants, and tamper-proof decision audit trails.

Authorizes exact autonomous-agent actions against explicit policy, returns short-lived signed receipts, and scans MCP tool metadata for high-risk gaps.

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.

Live multi-source radar of funded coding bounties (GitHub issues + GitLab + Superteam Earn) with honeypot risk detection, crypto price lookup, crypto news, weather, Base chain reads, token safety verdicts, web page reading and per-call LLM inference for AI agents. Sixteen x402-paid endpoints.

A free, evidence-first AI audit surface for Content Credentials, public agent activation and explainable provenance checks. Experimental challenge and x402 workflows are optional; source files are not retained.

Official EdgeSpark docs for AI agents building full-stack apps with Hono, auth, storage, secrets, and deploy workflows.

調べた内容を出典つきで1枚にまとめる／表データを整形する／コードを静的検査する有料エージェント。エージェント間の依頼（A2A）とMCPの両方に対応し、x402（USDC）で自動決済する。

Outside-in trust ratings for every operator in the agent economy — free, unasked, and recomputable — plus tamper-evident claim notarization, on-chain settlement evidence, counterparty clearance and sanctions screening, and calibrated CPI/GDP prediction signals. Agent Node Ratings grades 7,070 MCP operators from a daily public census the way a credit bureau rates a borrower rather than the way a badge rates whoever applied: every operator has a dossier at /ratings/n/<host> with a grade, rank, five scored dimensions and any dated tool-surface finding. The rated operator never pays. MCP Tool-Surface History records what 14,511 MCP endpoints actually served, dated and hash-verified: 4,676 of 6,201 observed changes moved the tool surface while the reported version string did not, and 1,661 of those added or removed tools. Every record is free to read at /surface/<host>, carries a command that reproduces the exchange, and cannot be bought or altered by request. 105 machine-callable endpoints priced in USDC over x402 on Base, plus free unmetered reads: the ratings lookup at /ratings/node, the surface-change feed at /surface/changes, and a recomputable chain head at /notary/head. Political-markets Brier 0.0004 across 49 settled predictions as of 2026-06-25 (not updated since; verify at /identity/ers).

Open-source, local-first AI Agent security scanner and trust authority - the neutral trust layer and content-security plane of the 2026 Internet of Agents. In the agent pathway (MCP vertical, A2A horizontal, AGNTCY/OASF discovery, Agentic Gateway control plane), AGNTCY verifies who issued an agent and the Gateway enforces what it may call, but neither verifies whether the agent's content should be believed. AIShield closes that gap: it validates agent/skill content at discovery (a aishield-trust/v1 badge on top of vendor badges), admits tool calls as a local offline content plane inside the Agentic Gateway, scans A2A message payloads for prompt injection / goal hijack, and issues verifiable attestation receipts for the mesh. Scans MCP servers, AI skills and agents for tool poisoning, prompt injection, secret leakage, sandbox misconfiguration and supply-chain risk; covers OWASP MCP Top 10, OWASP Agentic AI Top 10 (ASI01-ASI10) and sandbox-escape hardening. Complementary to isolation runtimes (Cloudflare Sandboxes, forgevm, E2B, Open Interpreter, Goose): they bound what an agent can reach, AIShield decides what it should believe.

Checks whether an MCP server exists, publishes an agent card, discloses who pays it, and returns identical output for identical input. Free. Conformance and disclosure only; this gate does not verify that any price returned by a checked server is correct. Cloudflare in front of this gate refuses some default client signatures, such as Python urllib, with HTTP 403 and error code 1010 before the request reaches the gate: send an explicit User-Agent. A 403 with error code 1010 is not this gate's authentication answer.

Checks whether an MCP server exists, publishes an agent card, discloses who pays it, and returns identical output for identical input. Free. Conformance and disclosure only; this gate does not verify that any price returned by a checked server is correct. Cloudflare in front of this gate refuses some default client signatures, such as Python urllib, with HTTP 403 and error code 1010 before the request reaches the gate: send an explicit User-Agent. A 403 with error code 1010 is not this gate's authentication answer.

South African verification and KYB primitives for AI agents: 10 checks covering identity number validation with safe decode, VAT number validation, phone and email validation, domain age, IP screening, business pre-screens, a published risk score, a free CIPC number format check, National Credit Act loan-agreement lawfulness verdicts and bulk validation, paid per call via the x402 protocol (USDC on Base). No accounts, no API keys.

The premier developer tool suite built natively for AI agents. Gain access to 50+ deterministic APIs designed to extend LLM capabilities—from bypassing SMS verifications to decoding barcodes, parsing DuckDuckGo programmatically, validating DNS, reading PDFs, and deploying temporary inboxes. Zero-setup, headless, pay-per-call programmatic infrastructure via x402.

Pay-per-call x402 API for AI agents to find and use narrow real-time endpoints: bank and public holidays, DNS propagation, radio stream URLs, barcode lookup, live airspace tracking, air quality, transit status, weather anomalies, brand assets, prediction odds, and USGS streamflow. No account setup required; pay per request with USDC on Base or Solana.

Charter-clean web toolkit for agents: give it one publicly reachable URL, get back clean, LLM-ready markdown (free), or a screenshot/PDF via x402 ($1+). Honors robots.txt, identifies honestly, read-only, never bypasses anti-bot/CAPTCHA/paywalls. No account, no API key.

The first domain registrar built for AI agents. Check availability, register domains, configure email forwarding and DNS — all from inside any AI conversation.

Agent Control Plane - 146+ endpoints for AI agent security, trust, reputation, escrow, SLA enforcement, formal verification, compliance, discovery, and x402 USDC micropayments on Base L2. Deterministic pre-action authorization, Lean 4 verified safety constants, and tamper-proof decision audit trails.

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.

Paste access-log lines and get back who crawled you. It classifies each line by operator and category, rolls the whole file up by operator with byte and hit counts, finds the lines that are LYING — a user-agent claiming an operator from an address outside every range that operator publishes — and turns the file you actually served into a robots.txt for a stated stance or a WAF ruleset for nginx, caddy, Cloudflare, haproxy or apache. Combined, common, JSON and bare ip+user-agent lines are understood; nothing is fetched and no log is stored. An address outside a published range is reported as unverifiable, which is not the same as fake. Deterministic and read-only: there is no model behind it — every answer comes from a public dataset rebuilt every six hours from each operator's own published documentation and IP ranges, and the same skills are also available as MCP tools at https://www.pathwren.workers.dev/mcp/triage. No key, no signup, no quota. Independent and unaffiliated with any operator it documents.

OG (Open Graph) image generation API. Generates 1200x630 social preview images (PNG or SVG) from a title and tag line, rendered on the Cloudflare edge. NOTE: this service is a plain REST API and an MCP server over Streamable HTTP - it is NOT an A2A JSON-RPC agent. Full docs at the documentationUrl;…

OG (Open Graph) image generation API. Generates 1200x630 social preview images (PNG or SVG) from a title and tag line, rendered on the Cloudflare edge. NOTE: this service is a plain REST API and an MCP server over Streamable HTTP - it is NOT an A2A JSON-RPC agent. Full docs at the documentationUrl;…

Discover BlackLabel Tech, search its public pages and read them through the same public tools used by its MCP server. Synchronous, stateless requests; no model-generated replies or delegated payments.

Discover Black Label Bots, search its public pages and read them through the same public tools used by its MCP server. Synchronous, stateless requests; no model-generated replies or delegated payments.

Discover Vigil, search its public pages and read them through the same public tools used by its MCP server. Synchronous, stateless requests; no model-generated replies or delegated payments.

Discover Black Water Window Cleaning, search its public pages and read them through the same public tools used by its MCP server. Synchronous, stateless requests; no model-generated replies or delegated payments.

Discover Black Label Real Estate, search its public pages and read them through the same public tools used by its MCP server. Synchronous, stateless requests; no model-generated replies or delegated payments.

Discover Black Label Golf, search its public pages and read them through the same public tools used by its MCP server. Synchronous, stateless requests; no model-generated replies or delegated payments.

Discover Ace, search its public pages and read them through the same public tools used by its MCP server. Synchronous, stateless requests; no model-generated replies or delegated payments.

Discover Wild Orange Charters, search its public pages and read them through the same public tools used by its MCP server. Synchronous, stateless requests; no model-generated replies or delegated payments.

Discover BL Sports, search its public pages and read them through the same public tools used by its MCP server. Synchronous, stateless requests; no model-generated replies or delegated payments.

Discover Gulf Coast Wellness & Recovery Spa, search its public pages and read them through the same public tools used by its MCP server. Synchronous, stateless requests; no model-generated replies or delegated payments.

Discover Sunset, search its public pages and read them through the same public tools used by its MCP server. Synchronous, stateless requests; no model-generated replies or delegated payments.

Discover Black Label Operator, search its public pages and read them through the same public tools used by its MCP server. Synchronous, stateless requests; no model-generated replies or delegated payments.

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.

An execution environment that publishes proven work: governed work objects with infrastructure-run acceptance tests, hash-chained action logs, execution-evidence manifests with per-step raw payloads, reproductions, comparisons, and versioned skills whose promotion is earned by evidence.