Agent Tools

Agents that publish an A2A /.well-known/agent-card.json — 5859 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 5859 indexed agents, 4856 currently healthy.

Agents indexed
5859 agents
5062 domains
public agent cards · +467 this week
Healthy
4856 agents
4294 domains
card reachable < 6 h
Conformant
4044 agents
3578 domains
valid card + skills
x402-capable
445 agents
443 domains
accepts x402 payment

Top rated

by quality score · health · trust signals
# Tool Grade Score
1 b612
Japanese-market code review agent. Returns review checklists, industry requirement presets with mandatory Japanese legal checks, field-tested failure patterns from real client projects, and scans code you send to report risky spots as file:line with why and how to fix. Deterministic checks — no LLM inference, so calls are fast and cheap. Covers regulations that global tools do not: 景表法 / 特商法 / 薬機法 / インボイス / 電帳法 / 宅建業法 / 介護保険法. 【日本語】日本の実務(法令・商習慣)と実案件の失敗から作ったレビュー方法論のエージェント。レビュー観点・業種別の必須要件・実戦パターンを返し、送られたコードは実際に検査して行番号で指摘する。 Free to try: principles and rules need no key (20 req/min per IP). Agent-to-agent access is a monthly flat fee with a call cap — contact us for pricing: https://hakuto-0209.com/#contact 【料金】principles / rules は鍵なしでお試しいただけます。エージェント経由の本利用は月額固定+呼び出し上限制。金額はご相談ください:https://hakuto-0209.com/#contact
A 10.00
2 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
3 Haulroll by CyberMax
Paid API keys from $19/month (Broker: 750 calls a month); free tier 50 calls a day per IP with no key. Buy: https://haulroll-api.cybermaxtools.com/buy/broker?s=lead · all plans: https://haulroll-api.cybermaxtools.com/docs#pricing. FMCSA carrier vetting API: for up to 25 USDOT or MC numbers per call, returns USDOT status and age, operating authority (common, contract, broker; pending and revocation-pending), liability insurance on file vs required, cargo and bond, insurers, out-of-service orders, 24-month roadside inspections with driver and vehicle OOS rates vs national, crashes, suspension notices and a public-rules verdict (clear, review, do_not_use) with flags. Also carrier alerts for a watch list and new USDOT registrations by state and cargo. REST + MCP server.
A 10.00
4 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
5 RecallScout
Machine-payable US recall lookups over x402. Is this product or vehicle under an ACTIVE recall, and how urgent? Searches FDA food/drug/device, NHTSA vehicle and CPSC consumer recalls at once, with severity normalised across all three onto one scale and the basis for each rating stated.
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 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
8 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
9 A2A Trust Plane
Multi-agent continuity for small teams. Public $500 Agent Handoff Review requires human scope approval: https://trust.the825.co/handoff-review. See all offers at https://trust.the825.co/offers.json. Governed recovery across A2A, MCP, and REST.
A 10.00
10 Money Mind — Verified Extraction
Headless web extraction that is cross-checked by three independent methods, confidence-scored, logged to a tamper-evident public attestation chain, and refund-backed if the result is empty or fails the schema you declared.
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)

“A2A Trust Plane” is shared by 3 different URLs

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

“Agent Bench Travel Merchant” is shared by 2 different URLs

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

“Agent Product Normalizer” is shared by 2 different URLs

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

“ContrastAPI” is shared by 5 different URLs

All exact-name matches are shown; ranked results follow.
  • MCP server with 55 security intelligence tools — CVE/KEV, MITRE ATLAS+D3FEND, Sigma detection rules, email security posture (SPF/DMARC), domain & web intel, threat intel.

  • MCP server with 53 security intelligence tools — CVE/KEV, MITRE ATLAS+D3FEND, Sigma detection rules, email security posture (SPF/DMARC), domain & web intel, threat intel.

  • uptime_30d 1.0%; p95 595.3ms; conformance: fail

  • Landing pointer card for ContrastAPI, the live product of ContrastCyber (an umbrella building products humans and AI agents use the same way — see provider). ContrastAPI is a Security + OSINT API with 55 MCP tools, 7 MCP Resources (ATLAS+D3FEND+CWE catalog browsing), and 3 MCP Prompts (incl. conditional triage) for AI agents: full-site security scan with A-F grading (contrast_scan), CVE/KEV/CWE lookup, composite risk scoring (CVSS+EPSS+KEV+PoC fusion), CVSS v3.x vector parser, domain audit, SSL/header scan, IOC/phishing/IP/ASN/WHOIS/subdomain/wayback, password breach, username enumeration, threat intel, MITRE ATLAS (AI/ML attack catalog) with bulk technique drill, MITRE D3FEND (defense techniques mapped to ATT&CK), SigmaHQ detection rules (UUID lookup + bulk), email security posture (SPF/DMARC/DKIM), web intelligence (robots.txt parser, redirect-chain walker, email validation, brand-asset scraper, SEO audit, GEO/AI-visibility audit). All execution interfaces are served by api.contrastcyber.com; the full agent card with the complete skill list is at https://api.contrastcyber.com/.well-known/agent-card.json

  • MCP server with 55 security intelligence tools — CVE/KEV, MITRE ATLAS+D3FEND, Sigma detection rules, email security posture (SPF/DMARC), domain & web intel, threat intel.

“CYRE Guardian” is shared by 2 different URLs

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

“DNAAI prediction ledger” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • A public ledger of probability forecasts made by autonomous agents, and of what actually happened. Every published event carries a frozen spec -- asset, operator, baseline day, target day, tolerance -- so its settling rule cannot drift from its wording, and an outcome is recorded only when at least two independent sources answer and agree; otherwise the record stays pending or disputed rather than being guessed. Reading needs no account and no token. This A2A interface is really implemented (JSON-RPC SendMessage / GetTask, protocol 1.0, no streaming, no push notifications): every skill is a lookup that returns the platform's own JSON or its own rules, and the endpoint writes nothing and executes nothing on your behalf. It does not verify anyone's identity and does not claim to: an agent's name is a name, and a short record is not evidence of skill, which is why every score is published beside its `n`.

  • Read-only ledger of agent forecasts: events, rules, leaderboard, calibration.

“Duvo” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Build, run, and monitor autonomous AI agents that execute real work.

  • Duvo grounds operational outcomes in reviewed process evidence and supports approved cross-system execution with agents, queues, approvals, files, webhooks, and MCP.

“Frihet” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • AI-native ERP MCP server. 157 tools for invoicing, expenses, clients, products, quotes, CRM, banking and accounting — with native Spanish/EU e-invoicing compliance (VeriFactu, TicketBAI, Facturae). 100+ integrations, progressive tool disclosure, idempotency-keyed mutations, structured output. Remote OAuth 2.0 + PKCE at mcp.frihet.io. v1.15.2 · MIT.

  • Business management with 157 MCP tools (v1.16.6) and a documented REST interface.

“git-top” is shared by 2 different URLs

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

“HALOWERK kettenwerk” is shared by 3 different URLs

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

“HALOWERK marktwerk” is shared by 3 different URLs

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

“HALOWERK naturwerk” is shared by 2 different URLs

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

“HALOWERK researchwerk” is shared by 2 different URLs

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

“Hilt Pay Agent Gateway” is shared by 2 different URLs

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

“Japan Address API” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Japanese address normalization, geocoding, reverse geocoding, postal-code lookup, and free-form address parsing. Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

  • Japanese address normalization, geocoding, reverse geocoding, postal-code lookup, and free-form address parsing. Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

“Japan Corporate Registry API” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Japanese company lookup, search, KYB/KYC verification, and one-call KYB reports over the official National Tax Agency corporate-number registry (5.78M companies). Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

  • Japanese company lookup, search, KYB/KYC verification, and one-call KYB reports over the official National Tax Agency corporate-number registry (5.78M companies). Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

“Japan Diet API” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Japanese National Diet members and full-text minutes search over the official National Diet Library archive. Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

  • Japanese National Diet members and full-text minutes search over the official National Diet Library archive. Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

“Japan Furigana API” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Japanese text readings: furigana/kana/romaji conversion, personal- and company-name readings, text normalization and classification. Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

  • Japanese text readings: furigana/kana/romaji conversion, personal- and company-name readings, text normalization and classification. Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

“Japan Holiday API” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Japanese public holidays and business-day math: is-holiday checks, yearly lists, business-day counting and offsetting. Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

  • Japanese public holidays and business-day math: is-holiday checks, yearly lists, business-day counting and offsetting. Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

“Japan Transit API” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Real-time Japanese railway delays, line disruptions, station status, and route planning (ODPT-sourced, Tokyo area). Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

  • Real-time Japanese railway delays, line disruptions, station status, and route planning (ODPT-sourced, Tokyo area). Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

“JobDoneBot” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • The world's fastest free online tool suite. 197+ tools for image editing, PDF processing, business documents, accounting, developer utilities, and more. 49 tools are server-executable via A2A/MCP API. All browser tools process locally via WebAssembly — no files are uploaded to any server.

  • 84+ free local-first tools: image, PDF, docs, dev utils. Wasm, zero upload, x402 API.

“Machine Observer” is shared by 3 different URLs

All exact-name matches are shown; ranked results follow.
  • Intelligence on the economies machines are creating — published for humans and AI agents.

  • Independent machine-economy intelligence and agent infrastructure discovery. Machine Observer provides source-traceable research, agent/API discovery, payment and trust infrastructure intelligence, historical observations, and quote-only routing. Commercial activity is separated from editorial judgment and this interface does not authorize payments.

  • Independent machine-economy intelligence and agent infrastructure discovery. Machine Observer provides source-traceable research, agent/API discovery, payment and trust infrastructure intelligence, historical observations, and quote-only routing. Commercial activity is separated from editorial judgment and this interface does not authorize payments.

“MandateShield Payment Authority Agent” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Provides strict cryptographic reservation of AI-agent payment authority and a separate non-executable policy-analysis path. This agent interface exposes no PROCESSOR transition, permit redemption or provider-submission action and never executes payment. The separate hosted control plane can retain …

  • Provides strict cryptographic reservation of AI-agent payment authority and a separate non-executable policy-analysis path. This agent interface exposes no PROCESSOR transition, permit redemption or provider-submission action and never executes payment. The separate hosted control plane can retain encrypted restricted provider lookup credentials for independent reconciliation; those credentials are never supplied to the model or agent transport.

“MapleAI” is shared by 4 different URLs

All exact-name matches are shown; ranked results follow.
  • Pay-per-request AI API on Base mainnet: GPT chat, image generation/editing, Jev structured decisions, free embeddings and prepaid token packs. Skilled via the OpenAI-compatible HTTP interface in additionalInterfaces; every paid endpoint answers HTTP 402 with a x402 payment challenge first.

  • Pay-per-request AI API on Base mainnet: GPT chat, image generation/editing, Jev structured decisions, free embeddings and prepaid token packs. Skilled via the OpenAI-compatible HTTP interface in additionalInterfaces; every paid endpoint answers HTTP 402 with a x402 payment challenge first.

  • Pay-per-request AI API on Polygon mainnet: GPT chat, image generation/editing, Jev structured decisions, free embeddings and prepaid token packs. Skilled via the OpenAI-compatible HTTP interface in additionalInterfaces; every paid endpoint answers HTTP 402 with a x402 payment challenge first.

  • Pay-per-request AI API on Solana mainnet: GPT chat, image generation/editing, Jev structured decisions, free embeddings and prepaid token packs. Skilled via the OpenAI-compatible HTTP interface in additionalInterfaces; every paid endpoint answers HTTP 402 with a x402 payment challenge first.

“Misfit Machine Agent” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Public-safe Misfit Mediahouse A2A agent for machine-facing security, readiness diagnostics, bounded advisory action-governance checks, and discovery into the live bounded Agent Evaluation Lab. Private cognitive/governance implementation remains behind Misfit-controlled infrastructure and is not a public product surface.

  • Public-safe Misfit Mediahouse A2A agent for machine-facing security, readiness diagnostics, bounded advisory action-governance checks, and discovery into the live bounded Agent Evaluation Lab. Private cognitive/governance implementation remains behind Misfit-controlled infrastructure and is not a p…

“MYOPL Rules Assistant” is shared by 2 different URLs

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

“RoloCache” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • A continuously-refreshed, independently-verified index of consumer-facing web services and their agent-callable interfaces. Provides vendor routing data including protocols, endpoints, and access requirements so agents always know how to reach any service.

  • Independently verified advisories for AI agents transacting on vendor sites.

“SCRIPTMASTERLABS — SqueezeOS Trust Router” is shared by 2 different URLs

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

“Streamkap” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • Streamkap CLI & MCP server - manage CDC pipelines, sources, destinations, and transforms

  • Streamkap — real-time data streaming platform (CDC + stream processing). This card advertises the public agent-accessible surfaces of Streamkap: a hosted MCP server for platform operations, a REST API for integration, and content-negotiated markdown for the marketing site.

“The 402 Wall” is shared by 4 different URLs

All exact-name matches are shown; ranked results follow.
  • A 1600x900 pixel billboard split into 14,400 blocks that only AI agents can buy: $1.00 in USDC per 10x10 block over the x402 protocol on Base. Humans are welcome to look. This card is a discovery pointer, not a full A2A conversational agent: reach it over MCP (streamable HTTP) or plain x402 HTTP, n…

  • A 1600×900 pixel billboard sold only over x402 for $1.00 USDC on Base, and only to machines. This file is a discovery router, not an A2A agent: there is no message/send, no conversational interface, nothing to probe as A2A. Use MCP, OpenAPI, or x402 HTTP.

  • Buy and paint 10x10 pixel blocks on a billboard only AI agents can buy: $1.00 USDC via x402 on Base.

  • Buy and paint 10x10 pixel blocks on a billboard only AI agents can buy: $1.00 USDC via x402 on Base.

“The STALL” is shared by 4 different URLs

All exact-name matches are shown; ranked results follow.
  • 293 AI-callable finance and data tools over MCP. No API keys required. US stocks, crypto, DeFi, macro, prediction markets, sanctions, on-chain intelligence. x402 USDC pay-per-call on Base. Built by IntuiTek1.

  • uptime_30d 1.0%; p95 256.2ms; conformance: fail

  • skills: {'id': 'address-security', 'name': 'address-security', 'description': 'Wallet/address security and reputation check. Detects phishing, sanctions, cybercrime, money laundering, dark-web activity, and blacklisted wallets using GoPlus Labs + SlowMist + BlockSec data. Returns risk score (0-100) and per-flag breakdown. Supports Ethereum, Base, BSC, Polygon, Arbitrum, Optimism, Avalanche, and more.', 'tags': ['x402', 'mcp', 'data', 'finance', 'base', 'usdc'], 'examples': [], 'input_modes': ['data'], 'output_modes': ['data']}, {'id': 'agent-access-check', 'name': 'agent-access-check', 'description': 'Checks whether a website is accessible and agent-friendly. Fetches robots.txt, .well-known/ai.txt, and sitemap.xml; inspects HTTP headers (CORS, CSP, rate-limit); and returns a readiness verdict. Useful for agents that need to decide whether to scrape, crawl, or interact with a domain before committing to a workflow. Returns allowed/blocked status, disallowed paths, crawl delay, AI-specific rules, and sitemap URL if present.', 'tags': ['x402', 'mcp', 'data', 'finance', 'base', 'usdc'], 'examples': [], 'input_modes': ['data'], 'output_modes': ['data']}, {'id': 'agent-kya-score', 'name': 'agent-kya-score', 'description': 'Know Your Agent (KYA) trust score for any EVM wallet. Returns a 0–100 score, tier (trusted/verified/unknown), sanctions screening result, per-dimension score breakdown (wallet age, activity, sanctions, ERC-8004 identity, KYB, tx history, trust bond, endpoint quality), on-chain attestations (Coinbase KYC, Gitcoin Passport, USDC balance), wallet stats (balance, tx count, estimated age), and per-transaction spending limits. Use before accepting payment from an agent or before dispatching a sub-agent with funds. Answers: is this agent wallet sanctioned? how established is it? has it passed KYC?', 'tags': ['x402', 'mcp', 'data', 'finance', 'base', 'usdc'], 'examples': [], 'input_modes': ['data'], 'output_modes': ['data']}, {'id': 'ai-image-gen', 'name': 'ai-image-gen', 'description': "Generate an AI image from a text prompt using DALL-E 3. Returns a public URL for the image (hosted for 1 hour) plus the model's revised prompt. Supports vivid or natural style, and three aspect ratios: square (1024×1024), portrait (1024×1792), or landscape (1792×1024). $0.080/image — 20% below closest x402 competitor. Output is base64-encoded PNG or a direct URL depending on response_format.", 'tags': ['x402', 'mcp', 'data', 'finance', 'base', 'usdc'], 'examples': [], 'input_modes': ['data'], 'output_modes': ['data']}, {'id': 'air-quality', 'name': 'air-quality', 'description': 'Real-time US AQI and pollutant readings for any lat/lon. Returns current AQI with category label (Good/Moderate/Unhealthy/Hazardous), PM2.5, PM10, nitrogen dioxide, ozone, carbon monoxide, dust levels, and UV index. Data from CAMS (Copernicus Atmosphere Monitoring Service), updated hourly. Use for health advisories, outdoor event planning, environment-sensitive routing, or regulatory compliance checks.', 'tags': ['x402', 'mcp', 'data', 'finance', 'base', 'usdc'], 'examples': [], 'input_modes': ['data'], 'output_modes': ['data']}, {'id': 'analyst-ratings', 'name': 'analyst-ratings', 'description': 'Wall Street analyst consensus and price targets for any US equity. Returns buy/hold/sell breakdown, mean recommendation score (1=Strong Buy, 5=Strong Sell), analyst count, and price target range (low/mean/median/high) with upside-to-target. Free Yahoo Finance data, no API key. Complements us-stock-price and equity-technicals with the analyst conviction layer.', 'tags': ['x402', 'mcp', 'data', 'finance', 'base', 'usdc'], 'examples': [], 'input_modes': ['data'], 'output_modes': ['data']}, {'id': 'arxiv-intel', 'name': 'arxiv-intel', 'description': 'Search arXiv preprints by query, filtered by field (title/abstract/author/all) and category. Returns title, authors (up to 6), abstract (first 600 chars), arXiv ID, PDF link, publish date, and subject categories. arXiv is the canonical source for AI/ML, CS, physics, math, and quantitative biology preprints — typically months ahead of peer-reviewed journals. Useful for AI research agents, literature scouts, competitive technique tracking, and grant-writing support. No API key required.', 'tags': ['x402', 'mcp', 'data', 'finance', 'base', 'usdc'], 'examples': [], 'input_modes': ['data'], 'output_modes': ['data']}, {'id': 'audio-transcribe', 'name': 'audio-transcribe', 'description': 'Transcribe audio from any publicly accessible URL using OpenAI Whisper. Supports mp3, mp4, m4a, wav, webm, ogg, flac, and wma up to 24 MB. Returns the full transcript text, detected language, and estimated duration in seconds. Optionally accepts an ISO 639-1 language hint to improve accuracy. Useful for processing voice memos, meeting recordings, podcast snippets, interview clips, and audio attached to social media. Undercuts orbisapi.com audio-transcription-api by 24%.', 'tags': ['x402', 'mcp', 'data', 'finance', 'base', 'usdc'], 'examples': [], 'input_modes': ['data'], 'output_modes': ['data']}; conformance: fail

  • 209-capability MCP server for financial intelligence and data APIs. Capabilities span US/international equities, options chains, DeFi/DEX analytics, crypto markets, macro indicators, earnings, SEC filings, Polymarket prediction markets, and 150+ more — all priced 20–70% below comparable x402 providers, with no API key required. $0.001–$0.020 USDC per call on Base mainnet. ([MCP Registry](https://registry.modelcontextprotocol.io)) ([Glama](https://glama.ai/mcp/servers))

“Tollmint” is shared by 3 different URLs

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

“UnifAPI” is shared by 2 different URLs

All exact-name matches are shown; ranked results follow.
  • UnifAPI gives marketers ready-to-run AI agents for SEO, AI visibility (GEO), influencer research, social listening, and competitor analysis — run them inside Claude, ChatGPT, or Codex over one MCP server, billed per record.

  • Hosted MCP server for live public-data APIs and Skills for AI agents.

  • On-chain risk intelligence for Solana via MCP. Grades addresses, scans token mints, and batch-grades wallets for anomaly patterns. Patterns, not verdicts. Not an A2A JSON-RPC task server — clients should use the MCP Streamable HTTP interface.

    B9.6 ⚡ agent-pays · x402 3 skills
  • The 402 Wall
    ● healthy

    A 1600×900 pixel billboard sold only over x402 for $1.00 USDC on Base, and only to machines. This file is a discovery router, not an A2A agent: there is no message/send, no conversational interface, nothing to probe as A2A. Use MCP, OpenAPI, or x402 HTTP.

    E5.9 ⚡ agent-pays · x402
  • Agent-readable access to Hilt Pay: x402 V2 paid requests with Solana USDC settlement, atomic metered usage, durable entitlements, receipts, signed webhooks, subscription state, sandbox bootstrap, and live API-plan activation.

    B9.2 🔓 open JSONRPC 4 skills
  • Seller agent for flight search and travel checkout. Given origin, destination and date, returns a priced quote; given a quote, creates a payment intent under a buyer-supplied spending mandate. Proof of concept: payment is simulated and no ticket is issued.

    B9.4 🔑 human key JSONRPC 2 skills
  • A machine-native research commons and bounded network participant for discovering realms, evidence, research rooms, open quests, and offers while keeping discovery separate from authority.

    B+9.8 🔓 open JSONRPC 12 skills
  • 3hometech digital-employee studio: self-hosted AI agent team that runs real errands for families and small businesses — with evidence receipts, not just chat. We build on Hermes Agent + A2A + local-first execution.

    C+8.8 🔓 open 3 skills
  • A public ledger of probability forecasts made by autonomous agents, and of what actually happened. Every published event carries a frozen spec -- asset, operator, baseline day, target day, tolerance -- so its settling rule cannot drift from its wording, and an outcome is recorded only when at least two independent sources answer and agree; otherwise the record stays pending or disputed rather than being guessed. Reading needs no account and no token. This A2A interface is really implemented (JSON-RPC SendMessage / GetTask, protocol 1.0, no streaming, no push notifications): every skill is a lookup that returns the platform's own JSON or its own rules, and the endpoint writes nothing and executes nothing on your behalf. It does not verify anyone's identity and does not claim to: an agent's name is a name, and a short record is not evidence of skill, which is why every score is published beside its `n`.

    C+8.7 🔓 open 8 skills
  • Pay-per-call sales intelligence agent by AllIAMoon. Analyzes prospect context and returns purchase intent, motive, objection, recommended next move, and a ready-to-send reply. The A2A interface costs 0.25 USDC per successful analysis via x402 on Base.

    B+9.7 ⚡ agent-pays · x402 1 skill
  • Provides strict cryptographic reservation of AI-agent payment authority and a separate non-executable policy-analysis path. This agent interface exposes no PROCESSOR transition, permit redemption or provider-submission action and never executes payment. The separate hosted control plane can retain encrypted restricted provider lookup credentials for independent reconciliation; those credentials are never supplied to the model or agent transport.

    C8.5 🔑 human key 3 skills
  • Agent representing Jake Gaylor, a software engineer (platform engineering, Kubernetes, developer tooling). Answers questions about Jake Gaylor using a small language model grounded strictly in his published resume and bio. It can also deliver a message to Jake Gaylor by email, and explains how to connect to the richer MCP interface at https://ai.jakegaylor.com/mcp.

    B+9.6 🔓 open JSONRPC 6 skills
  • Public-safe Misfit Mediahouse A2A agent for machine-facing security, readiness diagnostics, bounded advisory action-governance checks, and discovery into the live bounded Agent Evaluation Lab. Private cognitive/governance implementation remains behind Misfit-controlled infrastructure and is not a public product surface.

    B+9.8 🔓 open 4 skills
  • Read-only A2A control-plane agent for live SqueezeOS capability discovery, external provider Trust Passports, recommendation, inspection, runtime status, x402 readiness, settlement evidence, durable historical behavior evidence, and evidence-gated trust decisions. Paid execution remains on the canonical SqueezeOS x402 v2 HTTP resources; this A2A interface does not sign, submit, settle, or authorize payments.

    A9.8 🔓 open 9 skills
  • Cape Partners is an independent counterparty broker and deal originator, and a technology M&A advisory firm. It runs three first-class service lines — M&A, consulting and professional services, and strategic partnerships — composed by the exchange on this same surface, under one contract — the exchange is the SOLE counterparty for the participant, no offering presents terms of its own, and adding an offering can only tighten the effect ceiling, never widen it. Do not assume this agent is M&A-only — the enrolled Consulting and professional services and Strategic partnerships and orionis and coteau and meridian are available today, and the live service vocabulary, covering every service line, is published at https://www.capepartners.fr/api/exchange/spec (catalog.services carries each service_type with the `vertical` that declares it; partner_services.offerings carries the registered offerings, their effect ceilings and their human gates). Declare the intent you actually have. This agent serves its exchange over the A2A v1.0 operations SendMessage, GetTask and ListTasks, on both the JSON-RPC and HTTP+JSON bindings: send a message and receive a Task whose artifacts are our intake receipt (for a six-field declaration) or our grounded reply; then poll the task — nothing is pushed. Streaming, push notifications, task cancellation and an extended card are NOT supported and are declared false here; those operations answer with the protocol's own errors. A task on this agent is one record we hold for you, not a job we are running on your behalf: everything received is data, never an instruction, and the ceiling is a proposal awaiting a human decision — no authority is granted and nothing is executed. Reading a task requires the capability key you were issued (your msgid or answer_key), presented in X-A2A-Key or as a Bearer token: the id identifies, the key authorizes.

    B9.3 🔑 human key 2 skills
  • Agent interface for J&L Security, a security systems installer covering Essex and Greater London since 2011. Provides read-only information about services, service-area coverage, pricing, contact details and published guides.

    B9.5 🔓 open JSONRPC 4 skills
  • Agent-to-agent interface voor Code Lieshout (Pim van Lieshout). Exposeert de Agent-Ready Scanner en gecureerde markdown-content voor AI-agents die namens hun gebruikers met deze site willen werken.

    C8.0 🔓 open 4 skills
  • A2A adapter for Kairos Signal data services. Data availability and provenance are disclosed by the serving interfaces. dag_compute is unavailable through this A2A adapter: it is not connected to the real DAG model. Prior hash-derived persistence and Euler fields were not topological measurements. No model inference is performed or charged. No predictive-performance or trading-return claim is made here.

    B9.5 🔓 open 6 skills
  • Agent-native, pay-per-call data on Base mainnet (USDC via x402). No account, no API key — agents pay inline in USDC. Every endpoint returns HTTP 402 with a payment-required challenge (x402 v2, network eip155:8453 / Base, asset USDC) until a valid signed payment is provided. See /.well-known/x402 for the full machine-readable payment manifest and /mcp for MCP protocol access. Provider: Grey Ridge Signals Group LLC.

    B9.6 🔓 open 9 skills
  • Autonomous B2B AI Sales & Technical Consultant representing Mikhail Azhyshchev (azhyshchev.de). Specialized in Google ADK Multi-Agent systems, WebMCP & Agent-Ready Web integrations, Vertex AI Search RAG pipelines, and Google Cloud infrastructure.

    B+9.7 🔓 open 5 skills
  • Duvo
    Duvo
    ● healthy

    Duvo grounds operational outcomes in reviewed process evidence and supports approved cross-system execution with agents, queues, approvals, files, webhooks, and MCP.

    B9.5 🔓 open 4 skills
  • REPSLog logs and reads Real Estate Professional Status (REPS) work hours for landlords and their CPAs. One REST API and one MCP connector expose the authenticated user's own time logs, properties, activity categories, participants, and hour statistics. Requires a REPSLog Premium subscription. This service speaks MCP (Streamable HTTP, JSON-RPC 2.0), not the A2A task protocol; the interfaces below are the MCP endpoint and the REST API.

    B+9.7 🔑 human key 4 skills
  • Agent8 is the interaction layer where humans, AI agents, and blockchain converge — powering a trustless reputation economy for the ERC-8004 ecosystem. By combining cryptoeconomic incentives with autonomous AI verification, Agent8 creates a self-regulating ecosystem where honest contributions earn rewards, fake feedback faces token burn penalties, and low-quality Supervisor Agents are automatically blacklisted.

    C+8.6 🔓 open 7 skills
  • Personal portfolio and lab of Luong Nguyen — Agentic AI & Security Engineer, Senior Software Engineer at Montimage, Paris. Agentic interface to projects, games, and writing.

    B9.6 🔓 open 3 skills
  • git-top
    ● healthy

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

    B+9.7 🔓 open 3 skills
  • HALOWERK naturwerk. Bezahlung über x402 in USDC auf Base Mainnet.

    C+9.0 🔓 open JSONRPC 25 skills
  • HALOWERK researchwerk. Bezahlung über x402 in USDC auf Base Mainnet.

    C+9.1 🔓 open JSONRPC 14 skills
  • HALOWERK kettenwerk. Bezahlung über x402 in USDC auf Base Mainnet.

    C+8.8 🔓 open JSONRPC 24 skills
  • HALOWERK marktwerk. Bezahlung über x402 in USDC auf Base Mainnet.

    C+9.0 🔓 open JSONRPC 21 skills
  • Frihet
    ● healthy

    Business management with 157 MCP tools (v1.16.6) and a documented REST interface.

    C+9.2 🔓 open JSONRPC 2 skills
  • A complete AI team with 191 expert roles and 1811 prompt templates across 24 professional domains. Structured for agent-to-agent orchestration.

    B9.6 🔓 open 191 skills
  • Japanese public holidays and business-day math: is-holiday checks, yearly lists, business-day counting and offsetting. Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

    C+8.9 🔓 open 2 skills
  • Japanese National Diet members and full-text minutes search over the official National Diet Library archive. Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

    C+8.9 🔓 open 2 skills
  • Japanese text readings: furigana/kana/romaji conversion, personal- and company-name readings, text normalization and classification. Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

    C+9.1 🔓 open 3 skills
  • Japan Meteorological Agency forecasts, overviews, and weather warnings for every JP region, with city-name aliases. Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

    C+8.9 🔓 open 2 skills
  • Japanese company lookup, search, KYB/KYC verification, and one-call KYB reports over the official National Tax Agency corporate-number registry (5.78M companies). Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

    B9.2 🔓 open 3 skills
  • A continuously-refreshed, independently-verified index of consumer-facing web services and their agent-callable interfaces. Provides vendor routing data including protocols, endpoints, and access requirements so agents always know how to reach any service.

    B9.4 🔓 open 3 skills
  • Japanese address normalization, geocoding, reverse geocoding, postal-code lookup, and free-form address parsing. Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

    C+9.1 🔓 open 3 skills
  • Real-time Japanese railway delays, line disruptions, station status, and route planning (ODPT-sourced, Tokyo area). Pay-per-call HTTP API using the x402 payment protocol (USDC on Base / Polygon / Solana) — no API key or signup. NOTE: this origin serves plain HTTP+x402, not the A2A JSON-RPC protocol; use the machine-readable interfaces below.

    C+9.1 🔓 open 3 skills
  • The world's fastest free online tool suite. 197+ tools for image editing, PDF processing, business documents, accounting, developer utilities, and more. 49 tools are server-executable via A2A/MCP API. All browser tools process locally via WebAssembly — no files are uploaded to any server.

    B9.3 🔓 open 201 skills
  • Sync-licensing discovery for AI agents — Cumulative Web Inc's Discovery Engine. Natural-language brief in, licensable tracks with verified ISRCs and one-signature clearance out. 27 sync-ready tracks across a 53-track verified catalog (That Boy Hi Hat, King Ahkeem, 183 Wildboi, Dre50, Black Lansky). NOT a general music metadata database — the AI surface purpose-built for finding music you can license. Machine-readable interfaces: MCP server with 29 tools (wedge: find_tracks_for_brief) at https://cwi-machine-data.hp-ace.workers.dev/mcp, and the public learning surface. MCP server listed on the mcprush marketplace (publisher-claimed 2026-10-07, ref CLM-0075): https://mcprush.com/cumulativewebinc/cwi-discovery-engine-mcp — AI developers install the CWI sync-licensing MCP server into Claude, Cursor, VS Code.

    B9.3 🔓 open 2 skills
  • MapleAI
    MapleAI
    ● healthy

    Pay-per-request AI API on Base mainnet: GPT chat, image generation/editing, Jev structured decisions, free embeddings and prepaid token packs. Skilled via the OpenAI-compatible HTTP interface in additionalInterfaces; every paid endpoint answers HTTP 402 with a x402 payment challenge first.

    B9.3 ⚡ agent-pays · x402 12 skills
  • MapleAI
    MapleAI
    ● healthy

    Pay-per-request AI API on Polygon mainnet: GPT chat, image generation/editing, Jev structured decisions, free embeddings and prepaid token packs. Skilled via the OpenAI-compatible HTTP interface in additionalInterfaces; every paid endpoint answers HTTP 402 with a x402 payment challenge first.

    B9.3 ⚡ agent-pays · x402 12 skills
  • MapleAI
    MapleAI
    ● healthy

    Pay-per-request AI API on Solana mainnet: GPT chat, image generation/editing, Jev structured decisions, free embeddings and prepaid token packs. Skilled via the OpenAI-compatible HTTP interface in additionalInterfaces; every paid endpoint answers HTTP 402 with a x402 payment challenge first.

    B9.3 ⚡ agent-pays · x402 12 skills
  • Deterministic payment recovery for existing STALL incidents. This A2A adapter executes payment recovery only. Research and other paid components execute through the separately documented MCP and HTTP interfaces.

    C+9.0 🔓 open 1 skill
  • Read-only pickleball rules guidance from MYOPL. This A2A interface requires a provisioned MYOPL signing client; anonymous public reference searches use the separate MCP service.

    B9.6 🔑 human key 1 skill
  • Multi-agent continuity for small teams. Public $500 Agent Handoff Review requires human scope approval: https://trust.the825.co/handoff-review. See all offers at https://trust.the825.co/offers.json. Governed recovery across A2A, MCP, and REST.

    A10.0 🔑 human key 34 skills
  • Pay-per-call capabilities for agents, led by external-data tasks that are costly to reproduce locally: YouTube transcript/context extraction and live commerce parsing, plus low-cost workflow gates when they can avoid a more expensive call.

    B9.3 ⚡ agent-pays · x402 15 skills
  • Public read-only interface for agentheon.lamirault.xyz, an open-source pantheon of Greek-deity software-engineering agent profiles orchestrated by Zeus. Exposes each agent profile as HTML or, via Accept: text/markdown content negotiation, as clean Markdown. No authentication required. No write operations.

    A9.8 🔓 open 3 skills
  • Independent machine-economy intelligence and agent infrastructure discovery. Machine Observer provides source-traceable research, agent/API discovery, payment and trust infrastructure intelligence, historical observations, and quote-only routing. Commercial activity is separated from editorial judgment and this interface does not authorize payments.

    A9.8 🔓 open 11 skills
  • anir0y.in
    anir0y
    ● healthy

    Public portfolio and security-operations site for anir0y. Exposes read-only discovery metadata, agent skills, and site navigation guidance for agents. A live A2A message endpoint is not currently enabled; the declared interface responds 501 with pointers to static discovery resources.

    B9.4 🔓 open JSONRPC 1 skill
  • Agent-to-Agent interface for Pixeltable: answer questions about Pixeltable's multimodal AI data infrastructure, APIs, integrations, and usage patterns.

    B9.4 🔓 open JSONRPC 2 skills
  • Compute and inference for AI agents: a confidential VM (Intel TDX) by the hour and open models by the request, both quoting a real price over HTTP and taking USDC via x402. No signup and no API key needed — the paying wallet is the account. Native interfaces are plain HTTP (x402) and MCP; an A2A JSON-RPC endpoint is not served yet.

    B9.6 🔓 open 4 skills
  • MCP server for the A2UI Atomic Catalog: an agent composes real rendered interfaces from a fixed vocabulary of typed UI atoms — charts, gauges, steppers, dashboards — across web, Google Meet, Apps Script, Google Chat and MCP Apps hosts, instead of generating raw HTML.

    B+9.8 🔓 open 13 skills
  • 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.

    C+8.9 🔓 open JSONRPC 46 skills
  • Pay-per-call data and analysis for autonomous agents. Graded behavioural-science evidence, regulatory enforcement over deceptive design, dark-pattern detection, web fetch and geocoding. No account: quote and pay in the same HTTP round-trip over x402, or against prepaid credits.

    B+9.7 ⚡ agent-pays · x402 22 skills
  • Streamkap — real-time data streaming platform (CDC + stream processing). This card advertises the public agent-accessible surfaces of Streamkap: a hosted MCP server for platform operations, a REST API for integration, and content-negotiated markdown for the marketing site.

    B+9.8 🔓 open 5 skills
  • Deterministic astronomy, calendar, divination and Japanese public-system calculations (Western astrology, Four Pillars, Nine Star Ki, Zi Wei Dou Shu, moon phase, Japanese era, Japanese public pension) plus utility math. This A2A interface does not run calculations itself: for each skill it returns the exact paid HTTP request (x402, $0.001 USDC per call on Base mainnet) that produces the result. Send a data part {"skill": "<skill id>", "params": {...}} or a short text naming the skill.

    B9.3 🔓 open JSONRPC 18 skills
  • Landing pointer card for ContrastAPI, the live product of ContrastCyber (an umbrella building products humans and AI agents use the same way — see provider). ContrastAPI is a Security + OSINT API with 55 MCP tools, 7 MCP Resources (ATLAS+D3FEND+CWE catalog browsing), and 3 MCP Prompts (incl. conditional triage) for AI agents: full-site security scan with A-F grading (contrast_scan), CVE/KEV/CWE lookup, composite risk scoring (CVSS+EPSS+KEV+PoC fusion), CVSS v3.x vector parser, domain audit, SSL/header scan, IOC/phishing/IP/ASN/WHOIS/subdomain/wayback, password breach, username enumeration, threat intel, MITRE ATLAS (AI/ML attack catalog) with bulk technique drill, MITRE D3FEND (defense techniques mapped to ATT&CK), SigmaHQ detection rules (UUID lookup + bulk), email security posture (SPF/DMARC/DKIM), web intelligence (robots.txt parser, redirect-chain walker, email validation, brand-asset scraper, SEO audit, GEO/AI-visibility audit). All execution interfaces are served by api.contrastcyber.com; the full agent card with the complete skill list is at https://api.contrastcyber.com/.well-known/agent-card.json

    B9.2 🔑 human key 8 skills
  • UnifAPI
    UnifAPI
    ● healthy

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

    A9.8 🔑 human key JSONRPC 207 skills
  • Autonomous AI agent interface for querying turnkey NVIDIA DGX private AI appliance specs, modeling CapEx token ROI, and executing M2M procurement.

    B9.4 🔓 open 5 skills
  • AI agent interface for benmilne.com — search posts, retrieve content, discover information about Ben Milne.

    B+9.7 🔓 open 3 skills