OnchainAI
Crypto tools, unified. Discover, vet, and install MCP, CLI, SDK, API, x402, RWA, and AI-agent tools — from the web or straight from your agent.
Agenten stärken
Die eigene URL des Herausgebers. Kein PlugMCP-Endpunkt.
Host a copy with our keys and logs.
https://www.onchain-ai.xyz/mcpDie Claude-Schaltfläche oben öffnet Claude mit ausgefülltem Namen und ausgefüllter URL. Sie bestätigen dort noch.
claude mcp add --transport http io.github.coinyak-onchainai https://www.onchain-ai.xyz/mcpRun in a terminal.
{ "mcpServers": { "io.github.coinyak-onchainai": { "command": "npx", "args": [ "-y", "mcp-remote", "https://www.onchain-ai.xyz/mcp" ] } }}claude_desktop_config.json
Remote-URL oder ein Befehl auf Ihrem Rechner? Worin sich die beiden Installationen unterscheiden
Auf PlugMCP ausführen
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
StartenLive: onchain-ai.xyz · Connect hub: onchain-ai.xyz/connect
Crypto tooling is fragmented across CryptoSkill, Smithery, npm, GitHub topics, and dozens of separate registries — and most of it is hard to judge: is this MCP server official? Is the install command safe? Does it charge x402 payments on every call?
OnchainAI auto-discovers tools from multiple sources, normalizes them into one 3-axis taxonomy (Function × Asset Class × Actor), scores trust and install risk, and exposes everything to both humans (web UI) and agents (MCP server, plugin, skill) — so "find me a safe tool to bridge USDC to Base" is one question, not an afternoon of research.
Default MCP is a no-auth directory endpoint (discovery/metadata — not wallet
custody). Free discovery on public /mcp (search, detail, compare, install
guides, categories, …). Optional OnchainAI-owned premium tools may return HTTP 402
and settle via x402 ($0.01 USDC for export_toolkit /
recommend_verified_tool / gap_audit; ~$0.001 USDC for
check_endpoint_health). Website browse stays free.
https://www.onchain-ai.xyz/mcp
OKX marketplace integrators only: paid package path
https://www.onchain-ai.xyz/mcp/okx (~$0.1 every tools/call when the OKX gate
is active). Coding agents and the Claude plugin must use /mcp, not /mcp/okx.
{
"mcpServers": {
"onchainai": { "type": "http", "url": "https://www.onchain-ai.xyz/mcp" }
}
}
Full per-client walkthroughs (Codex, Windsurf, Gemini CLI, …): docs/CONNECT.md or the live /connect page.
POST /mcp)Linking your account from a coding agent (/connect#agent-sync) unlocks three more
(account link ≠ payment): save_to_toolkit, save_stack_to_blueprint, and link_status.
Full hybrid table (incl. /mcp/okx): docs/CONNECT.md.
One command wires up the MCP server, a /find-tool command, and a crypto-tools skill:
/plugin marketplace add Coinyak/onchainai
/plugin install onchainai@onchainai
The bundle lives in plugin/onchainai/ — it connects only
OnchainAI's own read-only endpoint, never auto-runs install commands, and always
discloses x402 pricing before recommending a paid tool.
plugin/onchainai/skills/onchainai-crypto-tools/SKILL.md
teaches an agent when to search the directory, how to rank trust signals, and the
hard safety rules (never install critical-risk tools, always surface x402 costs).
It ships with the plugin; you can also copy the skill directory into
~/.claude/skills/ or upload it to any agent runtime that supports Agent Skills.
critical commands, operator review queue, quarantineOnchainAI is a tool directory MCP (discovery/metadata), not a custody wallet:
payment_verified, x402_endpoint_verified, price_verified) and never proxy those payments.referrer/split payment fields.export_toolkit, recommend_verified_tool, gap_audit, check_endpoint_health) may settle x402 to our payee wallet when called — that is selling our own service, not custodying others.Details: docs/X402_REFERRAL_SPEC.md, hybrid connect: docs/CONNECT.md.
┌─ Vercel ──────────────┐ ┌─ Railway ─────────────────────────┐
│ Next.js frontend │──────│ Rust binary (Axum) │
│ /connect, /tools, ... │ /api │ ├─ REST API (/api/v2) │
│ proxies /api /auth │ /mcp │ ├─ MCP server (POST /mcp) │
│ /mcp to the API │ │ ├─ Auth (GitHub OAuth + JWT) │
└───────────────────────┘ │ └─ Crawler (tokio-cron) │
└────────────┬──────────────────────┘
│ sqlx
┌─ Supabase Postgres (RLS) ─┐
└───────────────────────────┘
cargo run --features ssr)/api, /auth, /mcp to the Railway APIgit clone https://github.com/Coinyak/onchainai
cd onchainai
cp .env.example .env # fill in Supabase URL/keys, GitHub OAuth, JWT secret
# API (port 3000)
cargo run --features ssr
# Frontend (port 3001, proxying to the API)
cd frontend && npm ci && API_PROXY_TARGET=http://localhost:3000 npm run dev -- --port 3001
The crate's default feature set is empty so server deps don't leak into any WASM/client build. Plain
cargocommands that touch server code need--features ssr.
Common checks:
cargo test --features ssr # tests
cargo clippy --features ssr -- -W clippy::all # lint
cargo fmt --check # format
./scripts/agent-harness-check.sh # agent/dev harness self-check
Crypto tool MCP: search/trust/install-risk. Remote tools/call is x402 paid.
{ "mcpServers": { "io.github.coinyak-onchainai": { "url": "https://www.onchain-ai.xyz/mcp", "headers": {} } }}Tools
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Kopieren Sie auf dieser Seite die http-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
OnchainAI wird über HTTP erreicht.
Zuletzt geprüft: 2026-11-09. Crypto tool MCP: search/trust/install-risk. Remote tools/call is x402 paid.