> ## Documentation Index
> Fetch the complete documentation index at: https://docs.hiveintelligence.xyz/llms.txt
> Use this file to discover all available pages before exploring further.

# FAQ

> Common questions about connecting to and building on Hive.

<AccordionGroup>
  <Accordion title="Do I need an account to try Hive?">
    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.
  </Accordion>

  <Accordion title="Which clients work?">
    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](/install).
  </Accordion>

  <Accordion title="Where does the data come from?">
    13 providers including CoinGecko, Alchemy, DeFiLlama, GoPlus, Codex, CCXT, Helius, and
    Hyperliquid. Every response names which one answered. See
    [data sources](/concepts/data-sources).
  </Accordion>

  <Accordion title="Do I need my own provider API keys?">
    No. Hive holds the upstream credentials and manages their rate limits. One Hive
    credential covers every provider.
  </Accordion>

  <Accordion title="Why does my agent only see eight tools?">
    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](/concepts/how-it-works).
  </Accordion>

  <Accordion title="What happens when I run out of credits?">
    Requests stop with a quota error. Hive does not bill overage, so a runaway agent produces
    errors rather than an invoice.
  </Accordion>

  <Accordion title="Can Hive place trades?">
    No. Hive is read-only market data. It does not execute trades, hold funds, or give
    financial advice.
  </Accordion>

  <Accordion title="Is my API key visible in my client config?">
    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.
  </Accordion>

  <Accordion title="I lost my API key. Can I retrieve it?">
    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.
  </Accordion>

  <Accordion title="Why is a price flagged as suspect?">
    Sources disagreed beyond a threshold. Rather than silently picking one, Hive sets
    `is_price_suspect` so your agent can surface the disagreement.
  </Accordion>

  <Accordion title="How do I know if data is stale?">
    Every material response carries `fetched_at`. Compare it against your own clock. Provider
    health for that call is in `runtime_status`.
  </Accordion>

  <Accordion title="Does Hive cover news or sentiment?">
    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.
  </Accordion>
</AccordionGroup>
