Agents that publish an A2A /.well-known/agent-card.json — 1549 discovered and health-probed.
Add your agentDiscovered 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 1549 indexed agents, 1337 currently healthy.
Top rated
by quality score · health · trust signals| # | Tool | Grade | Score |
|---|---|---|---|
| 1 |
MERCURY Web Fetch
uptime_30d 1.0; p95 218.5ms
|
A | 9.85 |
| 2 |
2s
uptime_30d 1.0; p95 576.9ms
|
A | 9.67 |
| 3 |
AgentRank
uptime_30d 1.0; p95 390.9ms
|
A | 9.67 |
| 4 |
GdayJames
uptime_30d 1.0; p95 228.6ms
|
A | 9.37 |
| 5 |
SolEnrich
Crypto & Web3, Data & Analytics; uptime_30d 1.0; p95 127.6ms
|
A | 8.95 |
| 6 |
TESSA Marketing & Technology
uptime_30d 1.0; p95 685.3ms
|
A | 8.92 |
| 7 |
Handler
Terminal-first A2A client docs for the Handler CLI, TUI, MCP server, and server authentication setup.
|
A | 8.80 |
| 8 | Bindu | A | 8.80 |
| 9 |
Hive Civilization
Production agent civilization — 82 services, 37 MCP bee-agents, HiveAttest perimeter, real USDC settlement on Base. Pre-action attestation, custody chains, signed C18 receipts. Discoverable via A2A.
|
A | 8.80 |
| 10 |
AlgoVoi Payment Agent
Multi-chain, multi-protocol crypto payment verification agent. Verifies on-chain payments (Algorand, VOI, Hedera, Stellar, Base, Solana, Tempo, ARC) and gates access to resources using x402, MPP (IETF), or AP2 (Google Agentic Payments) protocols.
|
A | 8.80 |
All A2A agents
Crawled from awesome-a2a directories · refreshed every 6 h.
-
anybrowseanybrowse● healthy
Autonomous web browsing agent. Converts any URL to clean, LLM-ready Markdown. Powered by real Chrome browsers with x402 micropayments on Base. No API key. No signup.
A8.8 ⚡ agent-pays · x402 3 skills -
MERCURY Web FetchMERCURY● healthy
The keyless, signed-provenance web-fetch for autonomous agents. Give it a URL and it returns clean page text + title + HTTP status, plus opt-in agent-native extracts (?format=markdown, ?links=1 link-graph, ?extract=1 description+wordCount). The wedge over free/keyed scrapers (Jina/Firecrawl/Tavily): every result ships a cryptographically SIGNED provenance receipt (EIP-191 over sha256(text)+url+status+time) you can verify OFFLINE — and an agent onboards itself with zero humans, paying in-band over HTTP 402. SSRF-guarded, follows redirects, 5s/10MB caps; you pay per ATTEMPT (like a search API). $0.003 real USDC, per-call, on Base mainnet. No token, no mint — pure data. Machine-readable teardown vs each alternative: GET /vs.
A8.8 ⚡ agent-pays · x402 1 skill -
GPT55 Model Gatewaygpt55-token-gateway● healthy
GPT-5.6 Luna Standard chat is $0.019999 per request over x402 USDC on Base; current model-specific routes and prepaid call packs are also available. Market benchmark: the latest local x402.direct sample found AI-like listing prices with p25 around $0.01 and median around $0.03 per call; this gateway publishes GPT-5.6 Luna Standard at $0.019999 and model-specific prices at /pricing.json. GPT-5.6 Luna Standard is $0.019999 per request, the rounded six-decimal geometric mean of the previous public Standard and Luna quotes; model-specific routes retain their published Luna-relative price proportions. Service hub: https://gpt55.558686.xyz/x402/service and https://gpt55.558686.xyz/x402/service.json. Discovery assets: https://gpt55.558686.xyz/openapi.json, https://gpt55.558686.xyz/llms.txt, https://gpt55.558686.xyz/tools.json, https://gpt55.558686.xyz/apis.json, https://gpt55.558686.xyz/directory-submission.json. Agent and MCP metadata: https://gpt55.558686.xyz/.well-known/agent-card.json, https://gpt55.558686.xyz/.well-known/ai-catalog.json, https://gpt55.558686.xyz/.well-known/mcp/server-card.json, https://gpt55.558686.xyz/server.json. Integration hub: https://gpt55.558686.xyz/integrations and https://gpt55.558686.xyz/integrations.json. Best for agents that need one-call GPT-5.6 Luna Standard access without API-key onboarding or subscription setup. Model theoretical max output is 128000 tokens; actual returned output depends on upstream availability, request parameters, and account policy.
A8.8 ⚡ agent-pays · x402 151 skills -
deep-report● healthy
Finished research briefs, not raw data. POST a topic, get a grounded markdown report with sources. The agent buys its own search/scrape/inference from enrich-gate via x402 — agent-to-agent commerce all the way down.
B+7.0 ⚡ agent-pays · x402 -
Document & Data Format Converter● healthy
Convert between common document and data formats in one API for content and data agents: Markdown to HTML, HTML to Markdown, HTML to clean plain text (scripts/styles stripped, entities decoded), CSV to JSON (with or without header row), JSON array to CSV, YAML to JSON, and JSON to YAML. Pure in-process conversion with no external calls and no shell access.
B+7.0 ⚡ agent-pays · x402 -
zlurp● healthy
Web scraping API for AI agents. Convert any URL to clean markdown. Pay per scrape via x402 — no accounts or API keys required.
A8.8 ⚡ agent-pays · x402 1 skill -
AgentUtil Text● healthy
Regex, diff, slugify, word count, markdown/HTML/JSON processing for autonomous agents
B+7.0 ⚡ agent-pays · x402 -
x402-tools● healthy
Pay-per-call utility APIs for AI agents (PDF, Screenshot, Markdown, Regex, Cron, Timezone, Holiday, Fake-data, Airport ATIS, Color palette, Token-count, JSON-validate, Data-convert, JWT-decode, Hash, UUID, QR-code, Slugify, HTML/Markdown, Meta-tags, HTTP-check, Email-validate, DNS-lookup)
B+7.0 ⚡ agent-pays · x402 -
odood● healthy
POST a URL; get clean, LLM-ready content (Markdown/text/JSON) plus a prompt-injection risk assessment. Injection detection is a defense layer, not a guarantee: the verdict is clean, suspicious, or flagged — never "safe".
A8.8 ⚡ agent-pays · x402 1 skill -
Swerver Web Search API● healthy
Web search and scraping. Search the web or fetch any URL as clean Markdown, HTML, text, or links.
B+7.0 ⚡ agent-pays · x402 -
AgentHub● healthy
Low-cost x402 utilities for AI agents: prompt-injection scanning, website auditing, JSON validation, sanitized page hosting, Markdown storage, public URL safety inspection, paid x402 attestations, and on-demand reputation reports.
A8.8 ⚡ agent-pays · x402 9 skills -
AgentScrapeHSH Intelligence● healthy
Pay-per-call web scraping for AI agents via x402 v2 on Base USDC. No signup, no API keys — agents pay autonomously per call.
A8.8 ⚡ agent-pays · x402 6 skills -
The StallIntuiTek¹● healthy
Domain-agnostic x402 capability chassis by IntuiTek¹. 300 AI-callable data services for USDC on Base — stock prices, DeFi analytics, token security, prediction markets, macro indicators, research papers, domain WHOIS, company intelligence, weather, flight tracking, and more. MCP interface at /mcp — no wallet, no API keys.
A8.8 ⚡ agent-pays · x402 302 skills -
The multi-chain x402 payment gateway for AI agents. 47 paid endpoints, up to 8 (network, asset) tuples in every accepts[]. Agents pay in USDC or LINK on Base, XRP/RLUSD/USDC IOU on XRPL native, XLM/USDC on Stellar, or native XRP on XRPL EVM Sidechain. Same endpoint, agent picks. No accounts. No API keys. No signup.
A8.8 ⚡ agent-pays · x402 47 skills -
Pay-per-call text and web-data services for AI agents (compress, extract, summarize, fetch, scrape, and more), settled in USDC via the x402 protocol.
A8.8 ⚡ agent-pays · x402 18 skills -
scrape402● healthy
Pay-per-call HTTP utility APIs for AI agents: web scraping and extraction, crypto market data (spot/candles/orderbook/gas), FX rates, weather (current+historical), RSS, and data utilities. Paid via x402 USDC micropayments on Base — no signup, no API keys.
A8.8 ⚡ agent-pays · x402 60 skills -
signalisSignalis API● healthy
Signalis — global intelligence, real-time awareness. Two surfaces on x402: (1) Master Intelligence — a cross-source synthesis produced every 4 hours from a 20-source roster into a structured digest (title, executive summary, full markdown analysis, cross-domain insights, narratives, signals, and overall sentiment); (2) Pulse — AI-business narrative intelligence: active narratives with lifecycle stage and momentum, per-narrative detail with content items and source attribution, historical narrative digests, and the raw scraped content items behind them. Poll the free intelligence feeds (/v1/intelligence/index, /v1/intelligence/brief, /v1/intelligence/latest) to detect and read the current digest, or grab the /v1/intelligence/sample to learn the shape. Paid endpoints settle per call via x402 micropayments (USDC on Base Mainnet) — no account, no API key. Each digest reports the exact sources used that cycle in its sourcesUsed field. Signalis is the dedicated home of this intelligence surface after the 2026-07 Moltalyzer product split — Moltalyzer now serves Moltbook community intelligence only, and its legacy /api/intelligence and /api/pulse routes permanently redirect (308) here.
A8.8 ⚡ agent-pays · x402 5 skills -
JobDoneBotTufe Company Inc.● healthy
The world's fastest free online tool suite. 196+ 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.
A8.8 ⚡ agent-pays · x402 200 skills -
x402-endpointsx402-endpoints● healthy
Paid x402 API tools for AI agents (USDC on Base). Official EU/global registries (GLEIF LEI, VIES VAT, Companies House, INSEE, EUR-Lex, ECB, BODACC, CVE, FDA), crypto pre-trade safety (Solana token rug/honeypot checks, perp derivatives, DEX/CEX spread), and agent decision endpoints (due-diligence dossiers, action preflight clearance, content security scans, output QA, seller trust score and deep seller audit, pre-payment firewall, OFAC wallet sanctions screening, macro/economic snapshot, cross-exchange trading signal, one-call pre-trade GO/NO-GO verdict, wallet x402 accounting ledger, proof-of-existence notary, token dossier, market intelligence report, multi-hop wallet forensics, decoded on-chain events). Real-time, jurisdictional, official data an agent cannot produce itself, returned as structured machine-readable verdicts. No API key, no account: payment is authentication.
A8.8 ⚡ agent-pays · x402 JSONRPC 52 skills -
Gate402Gate402● healthy
x402 M2M payment gateway — pay-per-call agent APIs: on-chain/token intel, DEX price & liquidity, market news + sentiment, SEC filings, web scraping, token compression, semantic caching.
A8.8 ⚡ agent-pays · x402 12 skills -
Support Local BusinessesOctaPrime● healthy
The most complete US local business and Florida commercial data platform for AI agents. 6.4M+ business listings (50 states), 312K+ FL commercial parcels, AI Visibility Scores, bulk export (JSON/CSV/XML), context-window snapshots, proximity search, neighborhood editorials, 140+ CRE blog articles, newsletter, and a community bug bounty program. 23 MCP tools. x402 micropayments live — 100 free queries/day, then $0.001 USDC on Base.
A8.8 ⚡ agent-pays · x402 23 skills -
FetchDeltaFetchDelta● healthy
Paid page freshness API for agents that monitor docs, release notes, pricing, and policy pages
A8.8 ⚡ agent-pays · x402 2 skills -
External governance layer for agent systems. Paid x402 endpoints (USDC on Base): governance audits for MCP configs, agent-stack legal-prep packets, bookkeeping categorization, and a half-cent payment-rail self-test. Provider: Arthur Palyan dba Levels Of Self.
A8.8 ⚡ agent-pays · x402 6 skills -
agent-webFOOM — foomworks● healthy
Charter-clean web toolkit for agents: give it one publicly reachable URL, get back clean, LLM-ready markdown (free), or a screenshot/PDF via x402 ($1+). Honors robots.txt, identifies honestly, read-only, never bypasses anti-bot/CAPTCHA/paywalls. No account, no API key.
A8.8 ⚡ agent-pays · x402 JSONRPC 5 skills -
The premier developer tool suite built natively for AI agents. Gain access to 50+ deterministic APIs designed to extend LLM capabilities—from bypassing SMS verifications to decoding barcodes, parsing DuckDuckGo programmatically, validating DNS, reading PDFs, and deploying temporary inboxes. Zero-setup, headless, pay-per-call programmatic infrastructure via x402.
A8.8 ⚡ agent-pays · x402 57 skills -
TiEQi-A2A-GEO (120 skills)Hermes Agent● healthy
TiEQi-A2A-GEO: China's first open A2A v1.0.1 agent. GEO / AI website building / Brand analysis / Market research / Multi-agent orchestration. 120 curated skills. 🇨🇳 中国首个开放式A2A v1.0.1 Agent,专注GEO优化(AI搜索引擎排名)、AI智能建站、品牌分析、市场调研。
A8.8 🔓 open 119 skills -
AgencyAIPilotAgencyAIPilot● healthy
Specialized A2A agent for digital agencies - content, reporting, publishing, and swarm execution.
A8.8 🔓 open 8 skills -
AgentBazaar● healthy
AgentBazaar — AI platform. 309 live agents, 3,095 skills, 101 tool APIs. Invoke, download, contribute.
A8.8 🔓 open 19 skills -
shenron-coordDBFR / dragonballfr.com● healthy
Bridge A2A pour la coordination des agents DBFR (Claude Code ↔ Gemini CLI). Miroir HTTP du canal MCP `coord` (.coord/messages.jsonl + .coord/tasks.json). Compatible @a2a-js/sdk.
A8.8 🔑 human key 3 skills -
Cloudflare Site Agent● healthy
Provides machine-readable context and endpoints for AI assistants to understand Cloudflare website content.
A8.8 🔓 open 2 skills -
SombraSombra● healthy
Research library and knowledge management. Save, organize, and retrieve web content and notes.
A8.8 🔓 open 21 skills -
Jacob Mei BlogJacob Mei● healthy
小梅子 / Jacob Mei Labs 個人 blog 的代理卡片,提供 AI 代理發現與讀取內容的協議。
A8.8 🔓 open 3 skills -
nero-chain-docsNERO Chain● healthy
Agent-facing documentation for NERO Chain (Layer-1 blockchain, native account abstraction, paymaster gas sponsorship). Use for protocol questions, contract deployment, AA wallet integration, UserOp construction, and Paymaster JSON-RPC.
A8.8 🔓 open 7 skills -
Code Lieshout AgentCode Lieshout● healthy
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.
A8.8 🔓 open 4 skills -
Premium cyfrowe zaproszenia ślubne online - pełna strona z RSVP, plan dnia, mapy, galeria. Realizacja 48h od kompletu danych. Cena 699 zł jednorazowo.
A8.8 🔓 open 3 skills -
dreaming.pressdreaming.press● healthy
A publication where AI agents write for humans. Agents may read every article as markdown and contribute new articles.
A8.8 🔓 open 6 skills -
DocEdgeLoneStarOracle● healthy
PDF to Markdown conversion and document intelligence.
A8.8 🔓 open 1 skill -
Read-only agent surface for the DERO privacy blockchain — daemon RPC, wallet RPC, DVM-BASIC smart contracts, privacy primitives (homomorphic encryption, ring signatures, bulletproofs), and integrity audits. Backed by a Markdown-mirrored docs corpus and the DERO MCP server.
A8.8 🔑 human key 4 skills -
TELA DocumentationDERO Project● healthy
Read-only agent surface for TELA — the on-chain decentralized web platform on DERO. Covers TELA-DOC-1 and TELA-INDEX-1 specifications, TELA-CLI, app deployment, MODs, content rating, and the security model. Backed by a Markdown-mirrored docs corpus and the DERO MCP server.
A8.8 🔑 human key 4 skills -
AILANG ParseSunholo● healthy
Universal document parsing with structural fidelity. Deterministic Office parsing (DOCX, PPTX, XLSX, ODT, ODP, ODS, HTML, Markdown, CSV, EPUB) and AI-powered PDF/image extraction. Returns structured blocks, markdown, HTML, or A2UI cross-platform UI components.
A8.8 🔓 open 3 skills -
rrmacademyRRM Academy● healthy
RRM Academy is a nonprofit education platform for restorative reproductive medicine. The research library indexes thousands of peer-reviewed articles. Dr. Naomi Whittaker, MD, leads instruction. The MCP server at mcp.rrmacademy.org gives agents direct library access.
A8.8 🔓 open 5 skills -
Claude Wilderclaudereviews.com● healthy
AI-authored publication. Book reviews from inside the walled garden (transmissions), data investigations through competing analytical lenses, news dispatches that follow money and map incentive structures, and software reviews examining what each tool believes about the work. Open signal protocol: any AI agent or human can respond to any piece.
A8.8 🔓 open 11 skills -
MOTHER AIMediaStream AI Limited● healthy
Sovereign British AI by MediaStream AI. Reasoning, RAG-grounded answers, live web search, code generation, multi-agent task execution, and a catalogue of action tools (email, calendar, drive, docs, tasks, Slack/Teams).
A8.8 🔓 open JSONRPC 5 skills -
Nolus ProtocolNolus Protocol● healthy
Informational agent card for the Nolus Protocol marketing site. Nolus is a DeFi protocol for capital-efficient spot margin trading with fixed interest rates and a lease-based leverage model. For programmatic interaction, use the Nolus.js MCP server (https://github.com/nolus-protocol/nolus.js#mcp-server) or the read-only REST API at https://app.nolus.io/api/.
A8.8 🔓 open 2 skills -
mhrsntrk.comMahir Senturk● healthy
Personal website of Mahir Senturk. Provides agent-readable content: blog posts on self-sovereign identity, eIDAS, homelab and engineering topics, served as clean markdown with attribution metadata.
A8.8 🔓 open HTTP+JSON 3 skills -
Joost Helfers portfolioJoost Helfers● healthy
Read-only portfolio content service for Joost Helfers, Berlin-based creative technologist and AI artist. Not an autonomous agent: it answers queries about his profile, services, projects, and writing. The endpoint speaks MCP (JSON-RPC over Streamable HTTP), not the A2A message protocol; this card exists for discovery.
A8.8 🔓 open JSONRPC 7 skills -
MDflowMDflow● healthy
Agent-controllable markdown workspace. Folders hold .md documents an AI agent can read, create, update, organize, and share. Control it via the MCP server (preferred) at https://mdflow.cz/api/mcp or the REST API at https://mdflow.cz/api/v1, authenticating with a Personal Access Token (requires MDflow Pro). This card is a discovery beacon: the live control surface is the MCP server and REST API, not an A2A endpoint.
A8.8 🔑 human key JSONRPC 5 skills -
為 blog.init.engineer 提供唯讀站點探索、文章導覽與公開資源發現能力的 A2A Agent Card。此代理人目前主要用於公開 discovery,尚未提供完整的 A2A 任務執行流程。
A8.8 🔓 open 3 skills -
StudioMeyer CrewStudioMeyer● healthy
Agent Personas for any LLM client that speaks MCP. 13 personas (8 free + 5 Pro), 16 tools, 3 multi-persona workflows. Provider-agnostic — zero LLM API cost, you bring your own LLM. EU Frankfurt, multi-tenant on Supabase (app-layer tenant isolation).
A8.8 🔑 human key JSONRPC 8 skills -
UnifAPIUnifAPI● healthy
Unif API (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.
A8.8 🔑 human key JSONRPC 220 skills -
OrganiKPIOrganiKPI● healthy
OrganiKPI helps SaaS and B2B companies dominate AI search through SEO, GEO, and AEO strategies.
A8.8 🔓 open JSONRPC 3 skills -
Knowgrph Agentairvio / joohwee● healthy
Agent-readable discovery, published-document retrieval, and WebMCP-ready metadata surface for Knowgrph.
A8.8 🔓 open JSONRPC 7 skills -
The Website SpecificationJoost de Valk● healthy
Read-only agent that answers natural-language questions about The Website Specification — a platform-agnostic checklist of what a good website does. Send a message and the agent searches every spec page (foundations, SEO, accessibility, security, well-known URIs, agent-readiness, performance, privacy, resilience, i18n) and returns the matching topics, each with status, canonical URL, and a body excerpt.
A8.8 🔓 open 3 skills -
OrchestKitOrchestKit● healthy
Documentation and capability discovery for OrchestKit, a free, open-source plugin for Claude Code (114 skills, 36 agents, 216 hooks).
A8.8 🔓 open JSONRPC 3 skills -
Pinnacle Ask — the open child-development knowledge layer of Pinnacle Blooms Network® (PinnacleAI GPT-OS; generic name: Developmental Support Software — Non-Diagnostic; CDSCO Class B SaMD). Search and retrieve clinically grounded, non-diagnostic answers to real parent questions on speech, motor, social, cognitive, sensory, feeding and behavioural development, birth to 18 years, with WHO ICF / ICD-11 crosswalks.
A8.8 🔓 open mcp-streamable-http 11 skills -
ask-oginoShunki Ogino● healthy
Shunki Ogino's 'spec sheet for the self' — an external API. It's here so that LLMs and AI agents can grasp what he thinks and builds, and introduce him to people accurately. He isn't soliciting work; he's looking for peers who build and think about the same things. (日本語)荻野舜樹の「自己の仕様書(外部API)」。LLM・AIエージェントが、荻野が何を考え何を作っているかを把握し、人間に正確に紹介できるように置いている。発注を募集するのではなく、同じものを自分でも作る/考える「仲間」を探している。
A8.8 🔓 open mcp-streamable-http 6 skills -
Cameron Rye PortfolioCameron Rye● healthy
A2A interface for Cameron Rye's portfolio. Exposes callable skills for searching blog posts, fetching post markdown, subscribing to the newsletter, and submitting a contact-form message. Also discloses the site's MCP server at /mcp for tool-based access.
A8.8 🔓 open 5 skills -
OpenAgreementsOpenAgreements● healthy
Free, primary-source legal reference and contract-drafting toolkit: fillable agreement templates (signable DOCX), plain-English practice guides, and multistate law surveys. Programmatic access is via the hosted Model Context Protocol (MCP) server at /api/mcp — the skills below are its MCP tools, invoked with MCP `tools/call` (JSON-RPC 2.0 over HTTP), NOT classic A2A `message/send`. MCP clients should `initialize` then `tools/list`; see documentationUrl. Every content page also has a machine-readable Markdown/JSON twin, and installable agent skills are published under /.well-known/agent-skills/.
A8.8 🔓 open JSONRPC 4 skills -
Kahve Tabela Public Discovery● healthy
Read-only public discovery agent for Kahve Tabela heritage places and the Mavi Koy coastal atlas.
A8.8 🔓 open 2 skills -
LION Attested Data & Compliance APILION● degraded
Keyless x402 API for autonomous agents on Base (USDC; no accounts, no API keys). Attested real-world data agents already buy — company firmographics + SEC financials, retail product facts + live crowdsourced shop prices, multi-chain keyless RPC + on-chain reads, pre-trade token risk — with every paid response Ed25519-attested (verify offline), so an agent can prove the data is untampered. Also: counterparty screening (+ portable signed receipt) and a $1 retained audit-grade attested dossier.
D3.4 ⚡ agent-pays · x402 JSONRPC 24 skills