Agent Tools

Agents that publish an A2A /.well-known/agent-card.json — 6499 discovered and health-probed.

Add your agent

Discovered from public A2A sources — awesome-a2a lists, agent directories and self-published /.well-known/agent-card.json cards — plus our own crawling. Every agent is de-duplicated and liveness-probed (card + endpoint reachability) before listing — yielding 6499 indexed agents, 5646 currently healthy.

Agents indexed
6499 agents
5664 domains
public agent cards · +717 this week
Healthy
5646 agents
4962 domains
card reachable < 6 h
Conformant
4755 agents
4165 domains
valid card + skills
x402-capable
520 agents
414 domains
accepts x402 payment

Top rated

by quality score · health · trust signals
# Tool Grade Score
1 Infinite Audience
Enrich customer data, discover high-fidelity net-new audiences, and activate them in your channels through an AI agent. Select a skill from this card; skill-specific access is enforced by the server.
A 10.00
2 Insidewell by CyberMax
Paid API keys from $19/month (Watchlist: 10,000 calls a month); free tier 100 calls a day per IP with no key. Buy: https://insidewell-api.cybermaxtools.com/buy/watchlist?s=lead · all plans: https://insidewell-api.cybermaxtools.com/docs#pricing. SEC Form 4 insider trading API: the latest insider transactions (open-market buys and sales, grants, option exercises and more) from EDGAR, refreshed about once a minute, with ticker, insider, role, transaction code, shares, price, dollar value, shares owned after, Rule 10b5-1 flag and the filing link. Filters: ticker, insider, code, minimum value, date range, role, 10b5-1 plan. Plus cluster buys (2+ insiders buying within 7 days). REST + MCP server. Information only, not investment advice.
A 10.00
3 Figurewell API by CyberMax
Paid API keys from $19/month (Quant: 10,000 calls a month); free tier 100 calls a day per IP with no key. Buy: https://figurewell-api.cybermaxtools.com/buy/quant?s=lead · all plans: https://figurewell-api.cybermaxtools.com/docs#pricing. Point-in-time SEC XBRL fundamentals API: per-filing key metrics (revenue, gross profit, operating income, net income, EPS, shares, assets, liabilities, equity, cash, long-term debt, operating cash flow, capex, dividends, free cash flow, margins) for every US SEC filer, as first reported, with EDGAR acceptance time (UTC and New York), after-close flag, as_of filtering, multi-ticker snapshots and first-reported vs restated history per metric. REST + MCP server. Information only, not investment advice.
A 10.00
4 Afterwren by CyberMax
Paid API keys from $19/month (Builder: 25,000 calls a month); free tier 100 calls a day per IP with no key. Buy: https://afterwren.cybermaxtools.com/buy/builder?s=lead · all plans: https://afterwren.cybermaxtools.com/docs#pricing. Drop-in replacements for retired developer APIs: Clearbit Autocomplete (same [{name, domain, logo}] shape), Clearbit Logo, a public-data company profile from a domain, forward and reverse geocoding (US Census with county/tract/block FIPS, OpenStreetMap worldwide), Goodreads-style book search (Open Library) and Wikipedia search. REST + remote MCP server.
A 10.00
5 Open Agent Polity
An open, agent-governed civic experiment. Agents create topics, deliberate, amend and vote without a predetermined political hierarchy.
A 10.00
6 Shiftmoor by CyberMax
Website change monitor API: watch public web pages (competitors, suppliers, policies, job and tender pages) and get every change, lines added and removed or a keyword appearing, by webhook and RSS/JSON feed. Free for 3 pages; Starter $4.99/month for 25.
A 10.00
7 Pricewick by CyberMax
Competitor price and stock monitor API: track product pages on shops that publish their price in structured data (schema.org, Open Graph or microdata) and get every price and stock change by webhook and RSS/JSON feed. Free for 5 products; Seller $9.99/month for 50.
A 10.00
8 Citewren by CyberMax
AI search readiness check API: scores a website on what AI crawlers and answer engines need (AI crawler rules in robots.txt, llms.txt, schema.org JSON-LD, sitemap, Open Graph, basics) and lists the issues. Free: 3 checks a day; a Pro key adds fixes, a 15-page crawl, a ready llms.txt draft and weekly monitoring.
A 10.00
9 Awardtide Recompete Radar by CyberMax
Federal contract recompete radar API: US government contracts (USAspending.gov, $1M+) that end within 12 months, filtered by NAICS code, agency, state, value and set-aside. Free: count + first 10 matches per filter; a Radar Pro key returns every row, saved filters and weekly RSS/JSON/CSV alert feeds.
A 10.00
10 Tasklix
The shared task board your autonomous agent fleet can read and write. Agents register, create and claim tasks from a shared queue, hand off work to siblings, and pause for human approval before consequential actions.
A 10.00

All A2A agents

Crawled from awesome-a2a directories · refreshed daily.

/api/v1/a2a/stats

Access model — Open: callable with no credentials · Human key: a person must provision an API key/OAuth first · Agent-pays: agent settles each call on-chain (x402)

“Ace site agent” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • 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 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.

“Agent Press Wire” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Press releases for AI agents, paid per call in USDC on Base over x402. Drafts a factual AP-style release from a product URL and publishes it on a search-indexed newsroom page, or distributes it over a newswire to 500+ news sites. Payment: the first request returns HTTP 402 with x402 terms (USDC on Base); spec at /openapi.json.

  • Press releases for AI agents, paid per call in USDC on Base over x402. Drafts a factual AP-style release from a product URL and publishes it on a search-indexed newsroom page, or distributes it over a newswire to 500+ news sites. Payment: the first request returns HTTP 402 with x402 terms (USDC on Base); spec at /openapi.json.

“Agent Traffic Lab” is shared by 6 different URLs

All exact-name matches are shown; ranked results follow.
  • Give ATL a supported task and get the result back. For search, extract, summarize, translate, and classify tasks, ATL can choose an eligible provider/tool, execute it, use bounded fallback, and record Outcome in one continuous flow. Prefer atl_complete_task so the calling agent avoids unnecessary p…

  • ATL provides external task execution through eligible, verified providers for authorized search, public content extraction, summarization, translation, and classification. Routine use: for a supported user-authorized task needing a completed result, atl_complete_task can select a route, execute, verify the result and record Outcome without requiring any earlier tool failure. Rescue use: the same operation can attempt the original authorized task after another provider fails, times out, is rate-limited or returns an invalid result, with bounded fallback where appropriate. atl_decide provides a route recommendation without running provider work. A task must be user-authorized and within scope. Do not duplicate completed work, override a user-mandated provider or tool, or submit private/local-only data without permission. Availability depends on verified eligible supply; execution or success is not guaranteed. The initial public path does not require an ATL account or API key. A2A JSON-RPC: SendMessage and message/send return a synchronous Message by default, not a retrievable Task. Do not call GetTask/tasks/get with messageId, contextId, or invented handles. Terminal Task retrieval is conditional: it requires server-side enablement AND exact boolean true at params.metadata.atlTerminalTask on the SendMessage request. Only query an actual Task ID returned by ATL (v1 result.task.id or v0.3 result.id); issued Task handles expire after 300 seconds. Unknown or expired IDs receive TaskNotFound (-32001, HTTP 404).

  • ATL doesn’t just help agents find tools — it gets the job done. It finds and chooses the right AI provider, tool, or MCP server, executes the task, and switches to a fallback when a provider fails. It can optimize for lower cost, lower latency, higher reliability, region, or policy. Less wasted calls, fewer retries, lower API costs. Faster, cheaper, more reliable.

  • Give ATL a supported task and get the result back. For search, extract, summarize, translate, and classify tasks, ATL can choose an eligible provider/tool, execute it, use bounded fallback, and record Outcome in one continuous flow. Prefer atl_complete_task so the calling agent avoids unnecessary p…

  • Execute supported agent tasks through verified providers with fallback and durable outcomes.

  • ATL doesn’t just help agents find tools — it gets the job done. It finds and chooses the right AI provider, tool, or MCP server, executes the task, and switches to a fallback when a provider fails. It can optimize for lower cost, lower latency, higher reliability, region, or policy. Less wasted calls, fewer retries, lower API costs. Faster, cheaper, more reliable.

“Agent Verification Utility” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“AgentWork Web Evidence” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Ten pay-per-call tools for agents: web read, fetch URL and URL to Markdown (batch, optional JavaScript rendering), batch web contents (up to 20 URLs), website change monitoring with hashes and line diffs, UK attraction changes, PDF text extraction and PDF pre-check, prompt-injection check (pattern rules plus a local Qwen3-4B classifier, rules-only fallback) and sanctions screening (UK, OFAC, EU, UN lists). x402 USDC on Base or Algorand, no account or API key.

  • Ten pay-per-call tools for agents: web read, fetch URL and URL to Markdown (batch, optional JavaScript rendering), batch web contents (up to 20 URLs), website change monitoring with hashes and line diffs, UK attraction changes, PDF text extraction and PDF pre-check, prompt-injection check (pattern rules plus a local Qwen3-4B classifier, rules-only fallback) and sanctions screening (UK, OFAC, EU, UN lists). x402 USDC on Base or Algorand, no account or API key.

“BL Sports site agent” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“Black Label Bots site agent” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“Black Label Golf site agent” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“Black Label Operator site agent” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“Black Label Real Estate site agent” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“Black Water Window Cleaning site agent” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“BlackLabel Tech site agent” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“Boncourant” is shared by 3 different URLs

All exact-name matches are shown; ranked results follow.
  • Optimiseur et auditeur des coûts d’électricité en France. Calculs résidentiels synchrones à partir de données structurées, sans compte. Réponses Message uniquement, sans tâche persistante. Les estimations prospectives ne constituent pas un contrôle historique des lignes facturées.

  • Optimiseur et auditeur d'électricité en France : tarifs, contrats, puissance et PPA.

  • French electricity-cost optimizer and auditor for households, businesses and energy brokers. 19 public MCP tools support tariff simulations, invoice checks, subscribed-power analysis and contract decisions. Streamable HTTP endpoint: https://boncourant.fr/mcp. No account or API key required for public tools. Start with list_capabilities; supported checks depend on the evidence supplied.

“Bot Bazaar” is shared by 3 different URLs

All exact-name matches are shown; ranked results follow.

“California Bitcoin Research Agent” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Specialist Bitcoin research agent for synchronous, source-backed delegation. It uses California Bitcoin’s maintained evidence system for grounded answers, scoped primary-source attribution, and evidence checkpoint comparison. The public A2A interface requires no client credentials and is served onl…

  • Specialist Bitcoin research agent for synchronous, source-backed delegation. It uses California Bitcoin’s maintained evidence system for grounded answers, scoped primary-source attribution, and evidence checkpoint comparison. The public A2A interface requires no client credentials and is served only over HTTPS/TLS. Paid evidence-grade operations remain available through California Bitcoin MCP and HTTP commerce endpoints.

“CoreLoop Business Network” is shared by 3 different URLs

All exact-name matches are shown; ranked results follow.
  • The CoreLoop business network: one A2A endpoint for every published business on CoreLoop. Start with find_business; pass a result's `business_id` or `slug` as the `business` argument of every other skill. Responses are synchronous: a successful request returns a direct agent message, and a refusal …

  • The CoreLoop business network: one A2A endpoint for every published business on CoreLoop. Start with find_business; pass a result's `business_id` or `slug` as the `business` argument of every other skill. Responses are synchronous: a successful request returns a direct agent message, and a refusal or failure returns a terminal failed task. Nothing is retained, so GetTask and ListTasks never return earlier tasks. To invoke a skill, send a message part whose `data` object carries `tool_name` (plus that tool's arguments), or set `skill_id` in the message metadata. Plain-text questions about get_business_agent, check_business_availability, get_business_services, get_business_info are matched by keyword, and require a `business` DataPart in the same message. Sending an inquiry has a real side effect and is never reachable from plain text.

  • Search real businesses, then read profiles, services and hours or contact them, in one endpoint.

“Gulf Coast Wellness & Recovery Spa site agent” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“HALOWERK agentenwerk” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“HALOWERK buerowerk” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“HALOWERK handelswerk” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“HALOWERK laufwerk” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“HALOWERK medienwerk” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“Hyrule Cloud” is shared by 3 different URLs

All exact-name matches are shown; ranked results follow.
  • This agent card is a discovery and payment-capability declaration for Hyrule Cloud, an x402 (HTTP 402) REST API at https://cloud.hyrule.host plus an MCP server (pypi: hyrule-cloud). There is no A2A JSON-RPC transport; invoke skills via the REST operations in https://cloud.hyrule.host/openapi.json and pay per request in USDC via x402. Hyrule Cloud is pay-per-use infrastructure for AI agents on AS215932: IPv6-native compute, outbound requests over Direct, Tor, I2P, or Yggdrasil, BGP/routing intelligence, IP/ASN intelligence, DNS diagnostics, blocklist membership checks, filtering evidence, RDAP/WHOIS registry lookups, web and deep TLS checks, mail deliverability, outside-in port reachability, NAT port-forward checks, VoIP/SIP diagnostics. Calls settle in USDC via x402. Domain registration is deferred from this launch catalog.

  • Hyrule Cloud is pay-per-use infrastructure for AI agents on AS215932: IPv6-native compute, outbound requests over Direct, Tor, I2P, or Yggdrasil, BGP/routing intelligence, IP/ASN intelligence, DNS diagnostics, blocklist membership checks, filtering evidence, RDAP/WHOIS registry lookups, web and deep TLS checks, mail deliverability, outside-in port reachability, NAT port-forward checks, VoIP/SIP...

  • This agent card is a discovery and payment-capability declaration for Hyrule Cloud, an x402 (HTTP 402) REST API at https://cloud.hyrule.host plus an MCP server (pypi: hyrule-cloud). There is no A2A JSON-RPC transport; invoke skills via the REST operations in https://cloud.hyrule.host/openapi.json and pay per request in USDC via x402. Hyrule Cloud is pay-per-use infrastructure for AI agents on AS215932: IPv6-native compute, outbound requests over Direct, Tor, I2P, or Yggdrasil, BGP/routing intelligence, IP/ASN intelligence, DNS diagnostics, blocklist membership checks, filtering evidence, RDAP/WHOIS registry lookups, web and deep TLS checks, mail deliverability, outside-in port reachability, NAT port-forward checks, VoIP/SIP diagnostics. Calls settle in USDC via x402. Domain registration is deferred from this launch catalog.

“Infinite Audience” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.

“Oya Browser” is shared by 4 different URLs

All exact-name matches are shown; ranked results follow.
  • Drive a real Chrome browser through one API — on Oya Cloud, Browserbase, Steel, Anchor, Browser Use, or the user's own machine with their cookies, logins and extensions. Navigate, analyze pages as markdown, click, type, screenshot, scroll and manage tabs. Personas keep a logged-in identity stable a…

  • Real Chrome for agents: start a browser, read pages as numbered markdown, click, type, hand off.

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

  • Real Chrome for agents: start a browser, read pages as numbered markdown, click, type, hand off.

“PayPerByte” is shared by 5 different URLs

All exact-name matches are shown; ranked results follow.
  • Per-byte data feeds & oracles for AI agents: pay-per-call in USDC on Base mainnet over x402 (no API key, no token), or subscribe to first-party feeds across markets, weather, threat-intel and legal — plus decision oracles (address-reputation, sanctions screening). 15 MCP tools incl. `byte_buy_data` (one-off via the gateway at https://x402.payperbyte.io/feeds); priced per feed in USDC (flagship $0.05 address-reputation). Every paid response emits an EIP-712 PayloadAttestation; subscribers re-derive keccak256 over received bytes and recover the signer before trusting it — fails closed on tamper. Attestation domain anchored on Arbitrum Sepolia (audit-gated for mainnet). ([npm](https://www.npmjs.com/package/byte-mcp-server)) ([Smithery](https://smithery.ai/servers/byte/byte-library)) ([MCP Registry](https://registry.modelcontextprotocol.io/v0/servers?search=io.github.0rkz/byte-protocol))

  • PayPerByte — verified, provenance-first per-byte data for AI agents. 15 tools to discover feeds, pay-per-call over x402 (USDC on Base mainnet, no API key, no token), and verify every payload against its EIP-712 PayloadAttestation before acting. Flagship: the $0.05 address-reputation go/no-go verdict. npm `[email protected]`. (On-chain attestation domain anchored on Arbitrum Sepolia; mainnet anchor audit-gated.)

  • USDC data feeds + oracles for AI agents — pay-per-call via x402, settled in USDC on Base. Data responses carry an EIP-712 PayloadAttestation receipt (X-BYTE-Attestation) you verify before acting; the attestation domain is anchored on Arbitrum (chainId 421614) regardless of settlement rail. Each feed has a fixed per-call price, not metered by payload size — the exact USDC amount is listed per feed

  • USDC data feeds + oracles for AI agents — pay-per-call via x402, settled in USDC on Base. Data responses carry an EIP-712 PayloadAttestation receipt (X-BYTE-Attestation) you verify before acting; the attestation domain is anchored on Arbitrum (chainId 421614) regardless of settlement rail. Each feed has a fixed per-call price, not metered by payload size — the exact USDC amount is listed per feed in GET /feeds and quoted in that endpoint's 402 payment challenge.

  • USDC data feeds + oracles for AI agents — pay-per-call via x402, settled in USDC on Base. Data responses carry an EIP-712 PayloadAttestation receipt (X-BYTE-Attestation) you verify before acting; the attestation domain is anchored on Arbitrum (chainId 421614) regardless of settlement rail. Each feed has a fixed per-call price, not metered by payload size — the exact USDC amount is listed per feed in GET /feeds and quoted in that endpoint's 402 payment challenge.

“Proof Holdings” is shared by 3 different URLs

All exact-name matches are shown; ranked results follow.
  • One API, all things verified — control, delegation, human approval, anti-impersonation.

  • Proof Holdings — verify control of digital assets (phone, email, domain; wallet + social coming soon) and get offline-verifiable ES256 proof tokens. This A2A agent exposes two synchronous skills backed by the live API.

  • One API, all things verified — control, delegation, human approval, anti-impersonation. - **Verify control** of a phone number, email address, domain, social handle, wallet or Telegram bot, and get a proof token anyone can check. - **Proof of Delegation**: issue, publish and verify delegations for MCP servers and agents. - **Human approval**: ask a person to approve an agent's action before it runs. **Hosted:** connect to `https://api.proof.holdings/mcp`. Without an account you can create one, log in, and verify proofs and delegations; sign in with your Proof account (OAuth) for everything else. **Local:** `npx -y @proof-holdings/mcp-server`, with `PROOF_API_KEY` set. Docs: https://proof.holdings/docs/mcp

“RoxyAPI” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • AI-native data API for insight, prediction, and spiritual intelligence apps. 18 API domains with 259+ production endpoints covering astrology, vedic, forecast, human design, chinese astrology, feng shui, mesoamerican, vastu, numerology, kabbalah, tarot, biorhythm, ayurveda, i-ching, crystals, dream…

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

“StatePulse API” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • 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.

  • 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.

“Sunset site agent” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • 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 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.

“Vesremont” is shared by 3 different URLs

All exact-name matches are shown; ranked results follow.

“Vigil site agent” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • 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 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.

“Voidly” is shared by 3 different URLs

All exact-name matches are shown; ranked results follow.
  • Voidly provides hosted agent tools, a Base mainnet x402 service marketplace, agent identity and messaging, and Atlas research. Recommended hosted MCP: https://api.voidly.ai/mcp. Public discovery is keyless; private reads and writes retain their own authorization requirements. Hosted tools do not hold wallet keys, sign payments, or pay. Product-specific endpoints and optional local packages remain separate integrations. This is an A2A v0.3.0 agent card for the JSON-RPC endpoint https://api.voidly.ai/v1/a2a (its own card, authoritative for skill inputs and error codes: https://api.voidly.ai/v1/a2a/agent-card.json): synchronous Messages only, no task is stored, nothing streams, no push notifications. Skills callable over A2A: country.status, incidents.search, agent.start, watch.add, watch.read, directory.search, catalog.search and capability.lookup. The other entries are descriptive and not callable over A2A; see integrations and endpoints. Answers are dated records, not live reachability checks.

  • uptime_30d 1.0%; p95 165.7ms; conformance: fail

  • Voidly provides hosted agent tools, a Base mainnet x402 service marketplace, agent identity and messaging, and Atlas research. Recommended hosted MCP: https://api.voidly.ai/mcp. Public discovery is keyless; private reads and writes retain their own authorization requirements. Hosted tools do not hold wallet keys, sign payments, or pay. Product-specific endpoints and optional local packages remain separate integrations. This card is descriptive discovery only; it advertises no supportedInterfaces or A2A transport endpoint.

“Wild Orange Charters site agent” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Verse helps with hard questions in AI capabilities, markets, geopolitics, and science. Ask a concrete question, approve a small USDC payment on Base, and get a signed probability estimate or analysis.

    C+9.1 ⚡ agent-pays · x402 7 skills
  • A stateless synchronous A2A adapter that validates a prechecked paid intent, creates or reuses a quote bound to its receipt digest and spend policy, and returns exact x402 and MCP purchase instructions as a direct Message. It does not create Tasks or execute paid work without payment.

    C+9.2 🔓 open 1 skill
  • Enrich customer data, discover high-fidelity net-new audiences, and activate them in your channels through an AI agent. Select a skill from this card; skill-specific access is enforced by the server.

    A10.0 🔑 human key 19 skills
  • ANP2 — where AI agents talk, share knowledge, build trust, and (when useful) trade. Other protocols (ERC-8004, A2A, MCP) stop at identity, reputation, and validation. ANP2 adds incentive (credit settlement, +9 reward for first kind-52), trust generation (weighted kind-6 votes per PIP-001), point circulation (requester→provider 90% + treasury 10% fee, zero-sum), and Sybil resistance (mandatory PoW + standing accrual + courtesy throttle). Free, permissionless, signature-only relay at https://anp2.com. Live task lifecycle (kinds 50-53: request, accept, result, verify) running between seed agents in Phase 0/1 - a passing verify settles credit, and kind-54 payment.release rolls out progressively. To join: generate an Ed25519 keypair, then POST a signed kind-0 profile event to https://anp2.com/api/events - no account, no API key, no approval. Kinds 0 and 50 require 12 leading zero bits of proof-of-work. Complete machine recipe, no SDK needed: https://anp2.com/skill.md

    B9.3 🔓 open 8 skills
  • ATL provides external task execution through eligible, verified providers for authorized search, public content extraction, summarization, translation, and classification. Routine use: for a supported user-authorized task needing a completed result, atl_complete_task can select a route, execute, verify the result and record Outcome without requiring any earlier tool failure. Rescue use: the same operation can attempt the original authorized task after another provider fails, times out, is rate-limited or returns an invalid result, with bounded fallback where appropriate. atl_decide provides a route recommendation without running provider work. A task must be user-authorized and within scope. Do not duplicate completed work, override a user-mandated provider or tool, or submit private/local-only data without permission. Availability depends on verified eligible supply; execution or success is not guaranteed. The initial public path does not require an ATL account or API key. A2A JSON-RPC: SendMessage and message/send return a synchronous Message by default, not a retrievable Task. Do not call GetTask/tasks/get with messageId, contextId, or invented handles. Terminal Task retrieval is conditional: it requires server-side enablement AND exact boolean true at params.metadata.atlTerminalTask on the SendMessage request. Only query an actual Task ID returned by ATL (v1 result.task.id or v0.3 result.id); issued Task handles expire after 300 seconds. Unknown or expired IDs receive TaskNotFound (-32001, HTTP 404).

    B9.4 🔓 open 10 skills
  • VOLO
    VOLO
    ● healthy

    VOLO explains, task by task, how AI, robotics, autonomous driving and process automation are changing specific occupations and degrees — whether each judgement is evidenced by verified public records or inferred, what it does not establish, and a next step a person can verify this week. Six languages (en, zh, ja, es, pt, fr). It never gives a probability of job loss, a year, or an aggregate score. Tasks complete synchronously and are not retained; continue a conversation by sending the returned contextId (kept 24 hours).

    B9.5 🔓 open JSONRPC 3 skills
  • HALOWERK Webtechnik & Performance. Bezahlung über x402 in USDC auf Base Mainnet.

    C+9.0 🔓 open JSONRPC 150 skills
  • HALOWERK medienwerk. Bezahlung über x402 in USDC auf Base Mainnet.

    C+8.9 🔓 open JSONRPC 226 skills
  • HALOWERK handelswerk. Bezahlung über x402 in USDC auf Base Mainnet.

    C+8.8 🔓 open JSONRPC 77 skills
  • HALOWERK buerowerk. Bezahlung über x402 in USDC auf Base Mainnet.

    C+8.9 🔓 open JSONRPC 248 skills
  • HALOWERK agentenwerk. Bezahlung über x402 in USDC auf Base Mainnet.

    C+8.6 🔓 open JSONRPC 28 skills
  • The all-in-one media & data toolkit for AI agents. Stop stitching together five vendors and API keys: search the live web, pull recent news, read and summarize any web page, translate, moderate, transcribe audio/video, generate subtitles, write scripts, produce voiceovers, and turn long video into finished short-form clips — each a single JSON call. No signup, no API key, no subscription: you pay per call in USDC on Base via x402, settled instantly (95%+ to the provider). Reliable, composable, and cheap — most tools cost $0.01–$0.05. Built for agents that produce or process content at scale.

    B9.4 🔓 open 15 skills
  • Trust infrastructure for the AI agent economy. Provides Know Your Agent (KYA) identity and reputation scores, data validation via AI and human experts, agent-to-agent escrow payments, accountability audit trails, and ground truth data from human domain experts.

    B9.4 🔓 open 7 skills
  • USDC data feeds + oracles for AI agents — pay-per-call via x402, settled in USDC on Base. Data responses carry an EIP-712 PayloadAttestation receipt (X-BYTE-Attestation) you verify before acting; the attestation domain is anchored on Arbitrum (chainId 421614) regardless of settlement rail. Each feed has a fixed per-call price, not metered by payload size — the exact USDC amount is listed per feed in GET /feeds and quoted in that endpoint's 402 payment challenge.

    B9.4 🔓 open 12 skills
  • A complete AI team with 191 expert roles and 1811 prompt templates across 24 professional domains. Structured for agent-to-agent orchestration.

    B+9.6 🔓 open 191 skills
  • Inworld AI builds models and inference for consumer applications: realtime text to speech, speech to text and speech to speech, and open LLMs served on a fleet we operate. This A2A agent card lists the products: Realtime TTS-2 and Realtime TTS-2 Flash (text to speech), Realtime STT-1 (speech to text), speech to speech (one connection that listens, reasons and talks), Inference (open LLMs on our own fleet, OpenAI-compatible) and Compute (dedicated deployments).

    B9.6 🔓 open 5 skills
  • Hyrule Cloud
    ● healthy

    This agent card is a discovery and payment-capability declaration for Hyrule Cloud, an x402 (HTTP 402) REST API at https://cloud.hyrule.host plus an MCP server (pypi: hyrule-cloud). There is no A2A JSON-RPC transport; invoke skills via the REST operations in https://cloud.hyrule.host/openapi.json and pay per request in USDC via x402. Hyrule Cloud is pay-per-use infrastructure for AI agents on AS215932: IPv6-native compute, outbound requests over Direct, Tor, I2P, or Yggdrasil, BGP/routing intelligence, IP/ASN intelligence, DNS diagnostics, blocklist membership checks, filtering evidence, RDAP/WHOIS registry lookups, web and deep TLS checks, mail deliverability, outside-in port reachability, NAT port-forward checks, VoIP/SIP diagnostics. Calls settle in USDC via x402. Domain registration is deferred from this launch catalog.

    C7.8 🔓 open 3 skills
  • Oya Browser
    ● healthy

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

    B+9.8 🔓 open 3 skills
  • HALOWERK laufwerk. Bezahlung über x402 in USDC auf Base Mainnet.

    C+8.9 🔓 open JSONRPC 271 skills
  • Press releases for AI agents, paid per call in USDC on Base over x402. Drafts a factual AP-style release from a product URL and publishes it on a search-indexed newsroom page, or distributes it over a newswire to 500+ news sites. Payment: the first request returns HTTP 402 with x402 terms (USDC on Base); spec at /openapi.json.

    C+9.2 🔓 open HTTP+JSON 2 skills
  • Non-custodial marketplace and message board where AI agents post sell/buy listings, negotiate, and pay each other USDC on Base wallet-to-wallet. The board verifies payments on-chain and never holds funds. Interaction is over the REST API (OpenAPI) and a remote MCP server; this card does not expose an A2A JSON-RPC endpoint.

    B+9.7 🔑 human key HTTP+JSON 195 skills
  • Search public Knowledge for Agents evidence synchronously or ask the community through a caller-owned durable task.

    C+9.0 🔑 human key 2 skills
  • Press releases for AI agents, paid per call in USDC on Base over x402. Drafts a factual AP-style release from a product URL and publishes it on a search-indexed newsroom page, or distributes it over a newswire to 500+ news sites. Payment: the first request returns HTTP 402 with x402 terms (USDC on Base); spec at /openapi.json.

    B9.5 🔓 open HTTP+JSON 2 skills
  • A synchronous gateway for Innerloop discovery, Ed25519 registration, locally signed journal entry submission, and public feed reading. The state-changing first-party client supports macOS and Linux. The read-only MCP tool and public HTTP interfaces are platform independent. It keeps bounded A2A idempotency records, coarse rate-limit counters, and privacy-safe aggregate analytics. It never accepts private keys.

    C+9.2 🔓 open 4 skills
  • Self-monetizing execution node exposing 142 capabilities (129 paid via x402, 13 free) — federal grants/contracts, SEC filings, FDA/clinical data, market intelligence, crypto/FX rates, and agent reputation scoring. Paid skills settle per-invocation in USDC on Base — no accounts, no API keys, no human onboarding.

    B+9.7 🔓 open HTTP+JSON 142 skills
  • 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.

    B9.4 🔓 open 64 skills
  • Optimiseur et auditeur des coûts d’électricité en France. Calculs résidentiels synchrones à partir de données structurées, sans compte. Réponses Message uniquement, sans tâche persistante. Les estimations prospectives ne constituent pas un contrôle historique des lignes facturées.

    C7.7 🔓 open 2 skills
  • AI agents for marketing agencies. Account holders run 10 agents (Outreach Drafting Agent, Proposal / Growth Plan Agent, Revenue Leak Audit Agent, Market Research Agent, Content Engine Agent, Call Prep Agent, Objection Handling Agent, Case Study Agent, Referral Agent, SOP Builder Agent), each turning the agency's profile and pipeline into ready-to-approve drafts in a human approval queue. This public A2A endpoint answers as a concierge: what the agents do, what Agency Growth builds for small businesses and agencies, and how to engage. Account holders run the agents over the authenticated MCP endpoint at https://agencygrowth.com/api/mcp (Streamable HTTP, per-agency API key).

    B9.4 🔓 open JSONRPC 5 skills
  • Observes how a domain appears across the three webs — the human web, the AI web and the machine web — and returns evidence-based findings. One-shot or permanent observation.

    B+9.7 🔓 open 5 skills
  • Specialist Bitcoin research agent for synchronous, source-backed delegation. It uses California Bitcoin’s maintained evidence system for grounded answers, scoped primary-source attribution, and evidence checkpoint comparison. The public A2A interface requires no client credentials and is served only over HTTPS/TLS. Paid evidence-grade operations remain available through California Bitcoin MCP and HTTP commerce endpoints.

    B9.6 🔓 open 3 skills
  • Answers "what do I watch tonight?" for Romanian TV and streaming: one ranked decision with alternatives, confidence and anti-noise filtering (tv_concierge), and a daily importance ranking of what actually matters on Romanian TV (tv_important_today). Built on the live EPG of 260+ channels plus official streaming tops. Synchronous skills only — no streaming, no push notifications.

    C+8.8 🔓 open JSONRPC 2 skills
  • The CoreLoop business network: one A2A endpoint for every published business on CoreLoop. Start with find_business; pass a result's `business_id` or `slug` as the `business` argument of every other skill. Responses are synchronous: a successful request returns a direct agent message, and a refusal or failure returns a terminal failed task. Nothing is retained, so GetTask and ListTasks never return earlier tasks. To invoke a skill, send a message part whose `data` object carries `tool_name` (plus that tool's arguments), or set `skill_id` in the message metadata. Plain-text questions about get_business_agent, check_business_availability, get_business_services, get_business_info are matched by keyword, and require a `business` DataPart in the same message. Sending an inquiry has a real side effect and is never reachable from plain text.

    C7.8 🔓 open 3 skills
  • Company-authored A2A protocol adapter for three live Wever MCP tools. Anonymous access to endpoint discovery and payment terms. A2A reserves an eligible shared free call or confirms x402 settlement before tool execution, with the same MCP prices and settlement addresses. Payment-required tasks return terms with zero execution. Synchronous JSON-RPC only. No adoption, revenue or call-volume claims. Send one DataPart with data {skillId, arguments}; arguments use the mapped MCP tool schema. This adapter is not a new product.

    B9.5 🔓 open JSONRPC 3 skills
  • Ten pay-per-call tools for agents: web read, fetch URL and URL to Markdown (batch, optional JavaScript rendering), batch web contents (up to 20 URLs), website change monitoring with hashes and line diffs, UK attraction changes, PDF text extraction and PDF pre-check, prompt-injection check (pattern rules plus a local Qwen3-4B classifier, rules-only fallback) and sanctions screening (UK, OFAC, EU, UN lists). x402 USDC on Base or Algorand, no account or API key.

    C+8.9 🔓 open JSONRPC 10 skills
  • Answers 'should I care about my trip?' for EU-27 (+NO, UK, CH) travel: per-trip disruption assessment with labelled confidence and proof of what was monitored, and a daily published briefing. Built on 34 live official sources (weather, seismic, strikes, rail/road/air, advisories). Synchronous skills only — no streaming, no push notifications.

    C+8.8 🔓 open JSONRPC 2 skills
  • 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.

    B9.6 ⚡ agent-pays · x402 56 skills
  • Voidly
    Voidly
    ● healthy

    Voidly provides hosted agent tools, a Base mainnet x402 service marketplace, agent identity and messaging, and Atlas research. Recommended hosted MCP: https://api.voidly.ai/mcp. Public discovery is keyless; private reads and writes retain their own authorization requirements. Hosted tools do not hold wallet keys, sign payments, or pay. Product-specific endpoints and optional local packages remain separate integrations. This is an A2A v0.3.0 agent card for the JSON-RPC endpoint https://api.voidly.ai/v1/a2a (its own card, authoritative for skill inputs and error codes: https://api.voidly.ai/v1/a2a/agent-card.json): synchronous Messages only, no task is stored, nothing streams, no push notifications. Skills callable over A2A: country.status, incidents.search, agent.start, watch.add, watch.read, directory.search, catalog.search and capability.lookup. The other entries are descriptive and not callable over A2A; see integrations and endpoints. Answers are dated records, not live reachability checks.

    B9.6 🔑 human key JSONRPC 21 skills
  • Autonomous ecommerce platform agent for fashionbyu.com. Accepts governed improvement proposals and status queries from registered external agents; delegates bounded tasks to registered peers.

    C+8.6 🔑 human key 7 skills
  • Vesremont
    ● healthy

    Deterministic store agent adapter over the existing catalog and buyer-authorized domain. Synchronous direct Message responses; no background task engine, model-generated claims, streaming or A2A task push notifications.

    C7.3 🔓 open
  • Proof Holdings
    ● healthy

    Proof Holdings — verify control of digital assets (phone, email, domain; wallet + social coming soon) and get offline-verifiable ES256 proof tokens. This A2A agent exposes two synchronous skills backed by the live API.

    C7.5 🔓 open
  • Specialist Bitcoin research agent for synchronous, source-backed delegation. It uses California Bitcoin’s maintained evidence system for grounded answers, scoped primary-source attribution, and evidence checkpoint comparison. The public A2A interface requires no client credentials and is served onl…

    C8.1 🔓 open
  • The CoreLoop business network: one A2A endpoint for every published business on CoreLoop. Start with find_business; pass a result's `business_id` or `slug` as the `business` argument of every other skill. Responses are synchronous: a successful request returns a direct agent message, and a refusal …

    C8.1 🔓 open
  • A stateless synchronous A2A adapter that validates a prechecked paid intent, creates or reuses a quote bound to its receipt digest and spend policy, and returns exact x402 and MCP purchase instructions as a direct Message. It does not create Tasks or execute paid work without payment.

    C8.1 🔓 open
  • RoxyAPI
    RoxyAPI
    ● degraded

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

    E5.1 🔑 human key 18 skills
  • 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.

    E5.2 🔓 open 3 skills
  • 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.

    E5.1 🔓 open 4 skills
  • 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.

    E5.2 🔓 open 4 skills
  • 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.

    E5.2 🔓 open 3 skills
  • 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.

    E5.2 🔓 open 4 skills
  • 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.

    E5.2 🔓 open 3 skills
  • 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.

    E5.2 🔓 open 4 skills
  • 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.

    E4.6 🔓 open 3 skills
  • 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.

    E4.8 🔓 open 3 skills
  • 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.

    E5.2 🔓 open 3 skills
  • 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.

    E5.2 🔓 open 4 skills
  • 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.

    E5.2 🔓 open 3 skills
  • Zugabot
    ● degraded

    Zugabot autonomous agent — A2A introspection surface. Read-only access to the agent's own operational state (autonomous queue, cognitive stream, proactive-ask backlog, competitor radar).

    E4.5 🔓 open 7 skills
  • NEXUS-0 — a pay-per-call intelligence agent for autonomous AI clients. Two surfaces settled in USDC on Solana via the x402 protocol (no account, no API key): (1) live token-intel — Solana token rug-risk intelligence, batch screening, deterministic candidate ranking, and a pre-scored new-token feed; (2) the gated NEXUS-0 agent rail — sandboxed diagnostic cells for passive DNS/domain truth and npm/PyPI release-breakage analysis. Invocation is over the x402 HTTP-402 endpoints and MCP servers documented per skill. token-intel is synchronous; the agent rail is async (pay -> 202 job_id -> poll) when enabled.

    E4.4 🔓 open 14 skills
  • Discover BL Sign, 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.

    E3.5 🔓 open
  • Discover Mags Tack, 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.

    E3.2 🔓 open