Use this when you need to check spot token balances for a specific wallet address on Hyperliquid L1 DEX. Returns all non-zero spot token holdings with available and held (in-order) amounts. Returns for each balance: 1. coin: token symbol 2. token: token index in spot registry 3. total: total bala...
Part of the Hyperliquid Spot API server.
Free to start. No card required.
AI agents call hyperliquid_get_spot_balances to retrieve information from Hyperliquid Spot API without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though hyperliquid_get_spot_balances only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"hyperliquid_get_spot_balances": {}
}
}See the full Hyperliquid Spot API policy for all 3 tools.
These attack patterns abuse exactly the kind of access hyperliquid_get_spot_balances gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Use this when you need to check spot token balances for a specific wallet address on Hyperliquid L1 DEX. Returns all non-zero spot token holdings with available and held (in-order) amounts. Returns for each balance: 1. coin: token symbol 2. token: token index in spot registry 3. total: total balance (hold + available) as string 4. hold: amount currently held in open orders 5. available: amount available for trading or withdrawal 6. entryNtl: entry notional value in USDC Input: wallet address (0x... format, 42 characters). Example output: { address: "0xabc...", balances: [{ coin: "PURR", total: "15000", hold: "5000", available: "10000", entryNtl: "350.50" }], count: 3 } Use this to check what spot tokens a Hyperliquid wallet holds before executing trades or analyzing portfolios. Do NOT use for perps positions -- use hyperliquid_get_perp_positions instead. Do NOT use for cross-chain wallet balances -- use wallet_get_portfolio instead. Do NOT use for Hyperliquid vault balances -- use hyperliquid_get_vaults instead. Do NOT use for EVM token balances -- use token_get_balance instead.. It is categorised as a Read tool in the Hyperliquid Spot API MCP Server, which means it retrieves data without modifying state.
Register the Hyperliquid Spot API MCP server in PolicyLayer and add a rule for hyperliquid_get_spot_balances: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Hyperliquid Spot API. Nothing to install.
hyperliquid_get_spot_balances is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the hyperliquid_get_spot_balances rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for hyperliquid_get_spot_balances. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
hyperliquid_get_spot_balances is provided by the Hyperliquid Spot API MCP server (https://hl-spot.api.klymax402.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Hyperliquid Spot API tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.