AI-native runtime for KuCoin trading strategies

No. Your strategy code connects to KuCoin and sends instructions according to your own logic, account permissions and integration method. TradingHost provides the runtime where that code runs.

No. KuCoin API access is provided by KuCoin. You are responsible for your KuCoin account, API permissions, credentials and compliance with KuCoin’s terms.

No. TradingHost is the cloud runtime where your strategy code runs. We do not provide signals, AI prediction models or pre-built strategies. With TradingHost you write or generate the strategy yourself (often with Cursor or Claude Code), keep it in GitHub as your code, and use TradingHost to run it in production. 3Commas, Cryptohopper and similar products own the strategy logic; TradingHost runs your strategy.

AWS and DigitalOcean give you raw compute. You handle OS updates, container orchestration, log shipping, secret rotation, region failover and uptime monitoring yourself. TradingHost gives you a managed runtime purpose-built for trading strategies: GitHub-native deployment, MCP-driven control from AI IDEs, log and health surfaces out of the box. If you want to operate the infrastructure yourself, AWS works. If you want the runtime as a managed service, TradingHost is the shorter path.

Yes. TradingHost runs Python strategies; pick the framework runtime that matches your stack or deploy your own repo.

Yes. TradingHost supports any language that can run inside a container.

KuCoin’s spot and futures venues are separate APIs (api.kucoin.com vs api-futures.kucoin.com) with separate API keys. In CCXT this is two exchange classes: kucoin for spot and margin, and kucoinfutures for futures.kucoin.com. Instantiate both with their own key + secret + passphrase, route orders to the correct client per symbol, and store the two credential sets as separate TradingHost secrets.

Yes, if your project is designed that way. You can run multiple strategy processes or services inside one runtime, or separate them into different runtimes for isolation and operational clarity. See the TradingHost runtime page for the multi-strategy model.

The fastest path is to fork a TradingHost framework runtime: CCXT, Freqtrade or Hummingbot for a ready-to-deploy project. Or connect your own GitHub strategy repo. Linking a GitHub repo and creating a strategy is free; runtime plans are listed on the pricing page.

In your GitHub-controlled secrets workflow. TradingHost reads them at runtime through GitHub repository secrets, environment secrets or your own approved secret-management process. TradingHost does not need custody of your API key, secret or passphrase. See platform secrets for the full handling model.

No. Strategies should never need withdrawal permissions. Use scoped permissions (read, trade) and IP whitelisting where appropriate.

Yes. TradingHost supports MCP-based control for AI IDEs including Cursor, Claude Code, GitHub Copilot and CLI-based AI agents. AI tools can inspect deployments, review logs, restart strategies and manage runtime workflows. MCP is a control and observability surface, not the trade execution path. See the MCP control surface for the full picture.

Both. The MCP control surface works equally well from CLI-based agents (Claude Code CLI, custom MCP clients, scripted MCP calls) and from inside an IDE. The GitHub-native deployment loop also works without any AI tooling: a regular git push to your main branch triggers a redeploy.

The runtime detects the crash and exposes the relevant logs and health information. Where supported, the affected strategy can be restarted without disrupting other strategies running in the same container. Your strategy code is still responsible for safe error handling, duplicate-order protection and risk controls. See observability for the logs and health surface.

Almost always one of three things. (1) The passphrase header for a v2 key must be base64 of HMAC-SHA256 of the raw passphrase, not the raw passphrase. (2) The KC-API-KEY-VERSION header must be set to "2" for v2 keys. (3) The signature payload is timestamp + UPPERCASE_METHOD + endpoint_with_query + body, with body as empty string on GET/DELETE. Missing any of these reproduces the same error class.

KuCoin doesn’t expose a static wss:// URL. Before connecting, POST to /api/v1/bullet-public (public feeds) or /api/v1/bullet-private (account/order feeds). The response gives you a one-shot token plus instanceServers[0].endpoint, the pingInterval and the pingTimeout. Connect to that endpoint with ?token=...&connectId=..., then ping on the interval returned. Tokens expire, so reconnect logic has to re-fetch.

No. Following a CFTC consent order entered March 30, 2026 against Peken Global Limited (KuCoin’s operator), KuCoin is permanently barred from accepting US persons unless it registers as a Foreign Board of Trade. The restriction applies to the KuCoin account, not to where strategy code is hosted, so deploying on TradingHost does not change eligibility.

Spot only. openapi-sandbox.kucoin.com covers spot endpoints and uses a fully separate login, API key set and fake balance. Futures, margin and options are not represented in the sandbox, so any strategy that touches api-futures.kucoin.com needs to be paper-traded another way (mock execution layer, very small live size, or framework-native dry-run) before scale-up.

TradingHost runs in the EU and US-East regions. Pick the region closest to the matching engine your strategy depends on. See the regions page for routing and proximity details.

No. TradingHost is focused on production runtime and deployment. Backtesting belongs in your research stack, framework or AlgoBuilder.