Skip to main content
No. The anonymous lane covers 25 material calls per IP per day, resetting at 00:00 UTC. Add the endpoint and start asking. Discovery calls do not count against it.
Nine have their own guide: Claude Code, Claude Desktop, Cursor, Windsurf, VS Code, ChatGPT, Grok, Codex CLI, and Gemini CLI. Any client that speaks MCP over Streamable HTTP works, whether or not it is listed. See install.
13 providers including CoinGecko, Alchemy, DeFiLlama, GoPlus, Codex, CCXT, Helius, and Hyperliquid. Every response names which one answered. See data sources.
No. Hive holds the upstream credentials and manages their rate limits. One Hive credential covers every provider.
That is intended. The root endpoint stays compact and routes to the rest through discovery, because a 607 tool list would crowd out the conversation and make selection worse. See how it works.
Requests stop with a quota error. Hive does not bill overage, so a runaway agent produces errors rather than an invoice.
No. Hive is read-only market data. It does not execute trades, hold funds, or give financial advice.
Not with OAuth, which is what every supported interactive client uses. You add only the URL and the client stores its own credential. Keys are for headless environments that cannot open a browser.
No. The full secret is shown once at creation; Hive stores only a hash and a short non-secret prefix. Disable the old key and create a new one.
Sources disagreed beyond a threshold. Rather than silently picking one, Hive sets is_price_suspect so your agent can surface the disagreement.
Every material response carries fetched_at. Compare it against your own clock. Provider health for that call is in runtime_status.
No, deliberately. Your model searches the web better than an API wrapper would. Hive covers what a model cannot get otherwise: live market state, on-chain data, and contract risk.