AI-native runtime for Mercado Bitcoin trading strategies

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

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

No. TradingHost is the cloud runtime where your strategy code runs. We do not provide signals, AI prediction models or pre-built bots. 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.

Yes. The exchange id is mercado. It exposes MB spot markets through the standard CCXT unified interface. If you are using Freqtrade or any other CCXT-based framework on TradingHost, set the exchange name to mercado. There is no official Hummingbot connector; that path requires a custom connector. See the CCXT framework runtime for the full setup story.

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 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 and secret. See platform secrets for the full handling model.

No. Strategies should never need withdrawal permissions. Use the minimum scope required (read plus trade) and enable any IP whitelisting Mercado Bitcoin offers on your key. Withdrawal-capable keys should be reserved for accounts you operate manually from a fixed host.

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.

Confirm which API generation you are calling. The new API v4 uses an /authorize flow that issues a token sent on subsequent private requests; the legacy TAPI v3 uses HMAC-SHA512 over the request path with TAPI-ID and TAPI-MAC headers. Mixing the two is the most common cause. Also check that your server clock is in sync and that the API key is enabled for the operation (read, trade, withdraw) you are calling.

Yes. BRL funding is handled by MB’s PIX integration outside the trading API. PIX runs 24x7 across the Brazilian banking system, so deposits typically credit instantly. Once BRL is on your MB account, strategies running in a TradingHost container call the MB API v4 to place orders against BRL pairs. TradingHost does not touch PIX or your bank credentials.

MB operates under Brazil’s Virtual Assets Law (Lei 14.478/2022). The Banco Central do Brasil’s Nov 2025 SPSAV resolutions (519, 520, 521) define licensing for virtual asset service providers, and the CVM oversees tokenized assets that qualify as securities. Full KYC is required for production trading; withdrawal limits are tied to verification tier; tokenized-asset endpoints may apply suitability or eligibility rules. None of this affects how your code runs in a TradingHost container; it affects what the MB account behind the API key is allowed to do.

For programmatic access, check which series are exposed via the API v4 markets endpoint at runtime. CVM rules may gate certain instruments. MBRL, MB’s BRL-pegged stablecoin issued on TRON (launched Nov 2024), is tradeable on MB’s order book and is a natural cash leg for BRL-side automation. Treat tokenized fixed-income RWA series on XRPL as discrete instruments with their own market structure rather than 24x7 crypto pairs.

TradingHost runs in the EU and US-East regions. Pick the region closest to the matching engine your strategy depends on. For Mercado Bitcoin specifically, US-East typically offers lower round-trip latency to São Paulo-region cloud endpoints than EU. 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.