Step 1: Add the endpoint
Pick your client. Every option below points at the same URL:- Claude Code
- Cursor
- VS Code
- Claude Desktop
Step 2: Sign in
The first time your client calls a Hive tool, it opens a Hive sign-in page in your browser. Sign in with GitHub, Google or a code sent to your email, then approve the connection. An account is created on first sign-in, on the Free plan with 10,000 credits a month. Your client can list Hive’s tools before you sign in, so it can show you the prompt. Every data call needs the sign-in. Running Hive from a server or script with no browser? Use an API key instead. See authentication.Step 3: Ask something live
Start a fresh session so the client picks up the new server, then ask:What is the current price of Bitcoin? Use Hive.Your agent calls
get_token_price. The answer should name a provider and a timestamp. If it
does, your agent is reading live data instead of guessing from training.
Try a harder one:
Research PEPE: is it liquid, how concentrated are the holders, and is the contract safe?That calls
research_token, which returns five sections, each with its own source. See
example prompts for prompts that trigger each of the nine tools.
Step 4: Read the receipt
Each answer, or each section of a multi-part answer, carries these fields: A section that could not be answered is listed undermissing, never filled in with a guess.
This is the part that makes the number quotable. Your agent can say where it got a figure and
how old it is, which matters when someone acts on it.
What it costs
Each tool has a fixed price in credits, from 1 for a price check to 5 for a full token report. Optional sections cost 1 credit each. A call that fails as a whole is refunded. See the nine tools for each price and limits for plans.Next
The nine tools
Inputs, answer shapes and prices.
Install your client
Exact config for all eleven supported clients.

