Skip to main content
Hive serves data. It does not place trades, hold funds, or give financial advice. Execution, risk limits, and every trading decision remain entirely yours.

The shape

A bot using Hive typically runs on a schedule rather than conversationally:
1

Authenticate with an API key

No browser in a cron job, so create an API key in the dashboard and keep it in your secret manager. See authentication.
2

Pull the state your strategy needs

One tool call per job: get_token_price for a price, market_positioning for funding, open interest and liquidations. Keep the set small; every call costs credits and time.
3

Check the receipts before acting

This is the step people skip. Reject data that is too old, came back with a degraded runtime_status, or is listed under missing, rather than trading on it.
4

Decide and execute elsewhere

Your venue integration handles the order. Hive is not in that path.

From the CLI

Each of the nine tools has a CLI command. With HIVE_API_KEY set in the environment:
--json prints an envelope with ok, data, and meta, where meta carries the provider and runtime status. The CLI has a built-in --jq filter if you want to pull one field out without piping:
Exit codes are stable enough to gate on. See CLI commands.

From a service

A long-running service can keep an MCP session open with the API key in the Authorization: Bearer header and call the same tools, or shell out to the CLI with --json. Both take the same arguments.

What it costs

Leaving a default metric out does not lower the price. Asking for fewer metrics makes the answer smaller, not cheaper.

Staying inside limits

Rate limits are per minute and credits are per month, and a bot can exhaust either. Practical habits:
  • Poll on the interval your strategy actually needs, not the fastest one available.
  • Use one multi-part tool instead of looping single lookups. market_positioning covers several venues in one call.
  • Handle the quota error properly. Hive hard stops rather than billing overage, so a bot that ignores the error simply trades on nothing.

The failure mode worth designing for

Data can be stale or degraded without being wrong-looking. A bot that acts on any number it receives will eventually act on a price fetched during a provider outage. Gate on fetched_at, runtime_status and missing explicitly, and treat a failed check as a reason to skip the cycle rather than to guess.