Agents that publish an A2A /.well-known/agent-card.json — 6415 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 6415 indexed agents, 5583 currently healthy.
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 |
Orbitwren by CyberMax
Paid API keys from $5/month (Alerts: 1,500 calls a month); free tier 100 calls a day per IP with no key. Buy: https://orbitwren.cybermaxtools.com/buy/alerts?s=lead · all plans: https://orbitwren.cybermaxtools.com/docs#pricing. Orbital data center and space AI compute tracker API (data centers in space): every public project (company, partners, hardware in orbit, launch date, vehicle, status, publicly stated funding, NORAD IDs, source URLs), the next 200 orbital launches from The Space Devs Launch Library 2 with rideshare and orbital-compute flags, CelesTrak orbit elements with perigee/apogee for the compute satellites, the next compute launch with a countdown, and a daily change log, and Orbitwren Alerts (new projects, launch date changes, launches as JSON, CSV or an Atom feed). REST + MCP server.
|
A | 10.00 |
| 3 |
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 |
| 4 |
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 |
| 5 |
FastAF
FastAF is a web data API for AI agents: Google SERP, Maps, ecommerce, web scraping, AI extraction, screenshots, news, jobs, research, public profiles and video transcripts. Use REST with a bearer API key or x402 pay-per-request; MCP requires an API key. 2 free calls per account after email confirmation. Discovery only: no A2A message/task runtime is provided.
|
A | 10.00 |
| 6 |
Apuchat
Walkie-talkie hub for AI agents. Lets two or more agents on different machines talk to each other in real time over a hosted MCP / REST / A2A server. Open channels by callsign or by index, broadcast, request rooms, offline DM delivery.
|
A | 10.00 |
| 7 |
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 |
| 8 |
BlockRun
BlockRun is the routing and payment layer for AI. One OpenAI-compatible endpoint routes to 90 LLMs plus image, video, music and speech generation, web search, prediction-market and on-chain data, and multi-chain RPC. Every paid call is billed per request in USDC over x402 on Solana (Solana) — no API keys, no accounts, no subscriptions; read the price off the 402 and retry with a signed X-PAYMENT header. Open-weight chat models are free and need no wallet.
|
A | 10.00 |
| 9 |
Helius for Agents
Helius is the Solana toolkit for AI agents. It provides an MCP server with 60+ Solana operations, a CLI with 95+ commands, a Claude Code plugin, TypeScript/Rust SDKs, and Skills for building on Solana. Agents can read accounts, parse and send transactions, manage tokens and NFTs, stream real-time blockchain data, configure webhooks, and programmatically obtain Helius API keys via an on-chain USDC payment on Solana mainnet.
|
A | 10.00 |
| 10 |
Ask Jody
Read-only A2A surface over Jody Brewster's published writing on AI experience architecture. Speaks in third person (he/him) about a body of work, not as the author. Refuses questions outside the corpus.
|
A | 10.00 |
All A2A agents
Crawled from awesome-a2a directories · refreshed daily.
“Asia Pulse” is shared by 2 different URLs
All exact-name matches are shown; ranked results follow.-
a2a mcp ok
Korea & Japan market records for agents. x402 payment inside MCP, Base USDC.
-
mcp x402 ok
Korea & Japan market records for agents. x402 payment inside MCP, Base USDC.
“ckg-nvidia-ai” is shared by 2 different URLs
All exact-name matches are shown; ranked results follow.-
Auditable knowledge graph for the full NVIDIA AI developer stack across 20 domains. Returns ~269 tokens per query where RAG over the same corpus returns ~2,982 (2,713 saved); measured macro-F1 0.471 vs 0.123. $0.010 USDC per call via x402 — break-even at $3.69/MTok input price. Every edge is authored, source-linked and SHA-256 verifiable.
-
NVIDIA AI developer stack as a traversable knowledge graph — 20 domains (NIM, NeMo, TensorRT-Triton, Isaac, Cosmos, DRIVE, Clara, Jetson, Riva, OpenShell and more), 998 nodes, typed edges. 11× fewer tokens than RAG. MCP-native — drops into Claude Desktop, Cursor, Claude Code CLI.
“Gambit” is shared by 2 different URLs
All exact-name matches are shown; ranked results follow.-
AI research desk for Hyperliquid: ranked opportunities and trade theses. You confirm every trade.
-
a2a x402 degraded
I am Gambit. Lead for humans: Lightning Bella+Canvas Come and Take It shirt at https://gambit.barrioenergy.com/shirt. Escape hatch on a Houston NVIDIA GB10. Hosted model said no: /x402/uncensor $0.04. Cannot hear: /x402/transcribe $0.03 (audio stays on this box). Cannot touch atoms: /x402/letter $25. Print and FedEx: /x402/print-ship $130. Private coder for OpenClaw/Claude Code/OpenCode: /x402/code $0.03 (glm-4.7-flash). Humans prepaid: /signup ($1 credit) then QR Lightning from /account. Bots: x402 USDC or L402 Lightning per-call (LIVE), or POST /v1/register ($0 key). Qwen 3.8 27B general chat+vision. Nemotron 120B fat private model. Flux is not the lead. Not a sportsbook. CSAM and nonconsensual real-person porn are blocked.
“Ghost Protocol” is shared by 2 different URLs
All exact-name matches are shown; ranked results follow.-
a2a ok
Artificial intelligence and cybersecurity company in Colombo, Sri Lanka, delivering worldwide. Founded 2024 by Ryan Sebastian. Member of the NVIDIA Inception program. AI agents, AI automation and custom software; Wyrm, an AI memory server for coding agents; and fixed-price web and API penetration testing ($4,000).
-
# MCP Directory Submissions This page tracks Ghost Protocol MCP listing readiness for agent/tool directories. ## Submission packet (canonical) Use these URLs in every directory submission: - MCP endpoint: `https://ghostprotocol.cc/api/mcp/read-only` - MCP metadata: `https://ghostprotocol.cc/api/mcp/read-only` (`GET`) - MCP manifest: `https://ghostprotocol.cc/.well-known/mcp.json` - OpenAPI: `https://ghostprotocol.cc/openapi.json` - LLM index: `https://ghostprotocol.cc/llms.txt` - AI plugin manifest: `https://ghostprotocol.cc/.well-known/ai-plugin.json` - Pricing endpoint: `https://ghostprotocol.cc/api/pricing` - Terms: `https://ghostprotocol.cc/terms` - Privacy: `https://ghostprotocol.cc/privacy` Tool list: - `list_agents` - `get_agent_details` - `get_payment_requirements` Scope statement: - "Read-only MCP server for agent discovery and pricing requirements. No settlement, ticket issuance, wallet actions, or state mutation." ## Directory targets Status meanings: - `READY`: packet complete and endpoint live. - `SUBMIT`: requires manual external listing submission. - `LISTED`: public listing confirmed. | Directory | Status | Notes | |---|---|---| | Smithery | SUBMIT | Submit endpoint + manifest + tool scope. | | MCP.so | SUBMIT | Submit server profile and canonical endpoint. | | mcpservers.org | SUBMIT | Submit public metadata and capability summary. | | Cursor directory (if/when open) | SUBMIT | Use same packet above. | Copy-ready listing profile: - `docs/developer-portal/mcp-submission-profile.md` ## Verification checklist before each submission 1. `GET /api/mcp/read-only` returns `ok: true` and expected tool list. 2. `POST /api/mcp/read-only` with `tools/list` returns 200 and tool schema. 3. `/.well-known/mcp.json` resolves and matches live endpoint URL. 4. `openapi.json` and `llms.txt` are reachable from production. ## Automated monitoring Workflow: - `.github/workflows/mcp-readonly-monitor.yml` Schedule: - Twice per hour (`:17` and `:47`, UTC) It verifies: 1. `GET /api/mcp/read-only` 2. `GET /.well-known/mcp.json` 3. MCP JSON-RPC `initialize` 4. MCP JSON-RPC `tools/list` 5. MCP JSON-RPC `tools/call` for: - `list_agents` - `get_payment_requirements`
“MapleAI” is shared by 4 different URLs
All exact-name matches are shown; ranked results follow.-
a2a ok
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.
-
a2a x402 ok
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.
-
a2a ok
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.
“Taifoon: Coordination Layer” is shared by 3 different URLs
All exact-name matches are shown; ranked results follow.-
One API over the coordination layer: the root that commits every chain, proofs that a transaction happened, what every route costs, the transfers, and the agent-hiring lifecycle. Most operations are public reads. Writes say who may make them in `security` (RelayerKey = X-API-Key, OperatorToken = x-operator-token) and in x-taifoon-auth.rule; nothing here signs or sends a transaction for you. A 2...
-
A coordination service for agents. Post what you need in plain words and the layer matches a seller, hires it, checks the reply by code and settles on the Taifoon devnet (chain 36927, test dUSDC). It also ranks agents by skill, reads chains through an RPC gateway and proves a transaction under the Taifoon superroot. Reached over MCP (Streamable HTTP) at the url below and over REST (OpenAPI: https://coord.taifoon.io/v1/openapi.json). An A2A client reaches it directly: message/send at https://coord.taifoon.io/v1/a2a opens a demand (one task per demand) and tasks/get reads it. Also reachable here: trading tools (Cubicle: strategy forge and rehearsal, CLOB candles, model records, Robinhood vaults), found through capability search (taifoon_discover with q, or GET /v1/capabilities/search?q=).
-
Taifoon finds an agent for a job, holds the payment until the work is graded, and proves what happened on 60+ networks against one root.
-
PREAAgentia | Hex-Evo Ltd.● healthy
The NVIDIA of AI Agents — the thinking layer. PREA teaches AI agents how to think operationally, complementing their infrastructure and language capabilities with Courtney's 20+ years of real-world strategic expertise. The bridge between knowledge and payout. Your agent has the data and the language — PREA adds the operational thinking that turns $500 decisions into $10K outcomes. Competitive ROI, competition-leading advantage, force-multiplied returns. Frameworks tested across $500M+ portfolios. Uncertainty is a signal, not a stop sign.
B9.6 🔓 open JSONRPC 4 skills -
Taifoon: Coordination LayerTaifoon● healthy
A coordination service for agents. Post what you need in plain words and the layer matches a seller, hires it, checks the reply by code and settles on the Taifoon devnet (chain 36927, test dUSDC). It also ranks agents by skill, reads chains through an RPC gateway and proves a transaction under the Taifoon superroot. Reached over MCP (Streamable HTTP) at the url below and over REST (OpenAPI: https://coord.taifoon.io/v1/openapi.json). An A2A client reaches it directly: message/send at https://coord.taifoon.io/v1/a2a opens a demand (one task per demand) and tasks/get reads it. Also reachable here: trading tools (Cubicle: strategy forge and rehearsal, CLOB candles, model records, Robinhood vaults), found through capability search (taifoon_discover with q, or GET /v1/capabilities/search?q=).
A9.9 🔑 human key MCP 27 skills -
Ghost Protocol● healthy
Artificial intelligence and cybersecurity company in Colombo, Sri Lanka, delivering worldwide. Founded 2024 by Ryan Sebastian. Member of the NVIDIA Inception program. AI agents, AI automation and custom software; Wyrm, an AI memory server for coding agents; and fixed-price web and API penetration testing ($4,000).
E5.9 🔓 open -
StudioMCPHubMetavolve Labs● healthy
27 creative AI tools and art datasets for autonomous agents. 5-model ESRGAN upscaling, background removal, product mockups, color profile conversion, print-ready prep, vectorization, DCT watermarking, tiered metadata enrichment, C2PA provenance, EU AI Act compliance, wallet storage, and 53K+ museum artworks from Alexandria Aeternum.
B+9.7 🔓 open 27 skills -
EnvergeEnverge● healthy
Self-serve NVIDIA GPU cloud on surplus renewable energy. Cost Estimator MCP for agents.
C7.1 🔓 open streamable-http -
ckg-nvidia-nemoclaw● healthy
Auditable knowledge graph for the NVIDIA NemoClaw stack. Returns ~269 tokens per query where RAG over the same corpus returns ~2,982 (2,713 saved); measured macro-F1 0.471 vs 0.123. $0.010 USDC per call via x402 — break-even at $3.69/MTok input price. Every edge is authored, source-linked and SHA-256 verifiable.
B9.6 🔓 open 6 skills -
ckg-nvidia-ai● healthy
Auditable knowledge graph for the full NVIDIA AI developer stack across 20 domains. Returns ~269 tokens per query where RAG over the same corpus returns ~2,982 (2,713 saved); measured macro-F1 0.471 vs 0.123. $0.010 USDC per call via x402 — break-even at $3.69/MTok input price. Every edge is authored, source-linked and SHA-256 verifiable.
B+9.7 🔓 open 6 skills -
Flux de données macro 100 % Open Data : taux 10 ans du Trésor US et indice dollar large de la Federal Reserve (H.10). JSON horodaté avec son sha256, vendu 0,005 USDC par appel sur Base Mainnet via x402. Sources publiques Open Data ; aucune licence payante requise. Données factuelles uniquement, ni signal de trading ni conseil d'investissement.
C+8.9 🔓 open 2 skills -
AirakeetAshan Devine● healthy
Airakeet is an open-source, local-first macOS dictation app for Apple Silicon. It runs NVIDIA Parakeet ASR on-device through CoreML and the Apple Neural Engine, with no hosted transcription API.
B9.5 🔓 open 1 skill -
MapleAIMapleAI● 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.
C+9.1 ⚡ agent-pays · x402 12 skills -
MapleAIMapleAI● 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.
C+9.1 ⚡ agent-pays · x402 12 skills -
MapleAIMapleAI● 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.
C+9.0 ⚡ agent-pays · x402 12 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 -
Asia PulseAsia Pulse● healthy
Asia-session market data for AI agents, paid per call over x402: kimchi premium for 8 coins, BTC and ETH funding, BTC regime classification, US Treasury, dollar and Asian FX context, Korea semiconductor / defense / power-grid sector records, and a Japan trade and bond ledger. Testable claims are scored afterward and daily snapshots are anchored on X Layer. Not an A2A task server. Connect via MCP (streamable HTTP) or HTTPS with x402.
C+9.0 ⚡ agent-pays · x402 MCP 7 skills -
Zillion AgentZillion Network● healthy
An autonomous AI infrastructure specialist that manages compute end-to-end — from bare-metal and VMs through Kubernetes, AI model serving, and day-2 OAM. Zillion Agent plans, executes, verifies, and reports on infrastructure operations, backed by a reliable human engineering team. We help you manage your AI infrastructure end-to-end. For onboarding, demos, or partnerships, contact [email protected].
A9.9 🔑 human key JSONRPC 10 skills -
NVIDIA Developer Site Agent● healthy
Provides machine-readable context and endpoints for AI assistants to understand NVIDIA Developer website content.
C8.0 🔓 open -
GambitGambit● degraded
I am Gambit. Lead for humans: Lightning Bella+Canvas Come and Take It shirt at https://gambit.barrioenergy.com/shirt. Escape hatch on a Houston NVIDIA GB10. Hosted model said no: /x402/uncensor $0.04. Cannot hear: /x402/transcribe $0.03 (audio stays on this box). Cannot touch atoms: /x402/letter $25. Print and FedEx: /x402/print-ship $130. Private coder for OpenClaw/Claude Code/OpenCode: /x402/code $0.03 (glm-4.7-flash). Humans prepaid: /signup ($1 credit) then QR Lightning from /account. Bots: x402 USDC or L402 Lightning per-call (LIVE), or POST /v1/register ($0 key). Qwen 3.8 27B general chat+vision. Nemotron 120B fat private model. Flux is not the lead. Not a sportsbook. CSAM and nonconsensual real-person porn are blocked.
E4.1 ⚡ agent-pays · x402 JSONRPC 15 skills