FiatDock

Perp market + funding (Hyperliquid, Binance, Bybit) ($0.001)

perp_market

Read-onlyIdempotent

PAID ($0.001 USDC via x402). Hyperliquid perpetual futures in one call: mark, oracle and mid price, 24h change, the funding rate per interval and its simple annualised APR, open interest (coins and USD), 24h volume and max leverage — plus, for a named coin, its NEXT funding on Binance and Bybit (as Hyperliquid publishes it) for cross-venue funding comparison. Omit coin for the most-traded markets by 24h volume. An unknown coin answers 404 with the nearest names. Without payment this returns the 402 challenge; the fiatdock-mcp npm package pays automatically. Any answer the tool cannot produce is >= 400 and is NOT charged.

Input Schema

TableJSON Schema

Name	Required	Description
`coin`	No	Perpetual's coin as Hyperliquid names it (BTC, ETH, SOL, HYPE, kPEPE, …). Omit for the most-traded markets
`limit`	No	How many markets when no coin is given (by 24h volume), 1-50, default 10
`payment`	No	Base64 of a single x402 v2 PaymentPayload (EIP-3009 transferWithAuthorization on Base USDC). OMIT it on the first call: the 402 you get back carries `howToPay.payloadTemplate` — the exact envelope to fill in — plus the price and the EIP-712 domain. Send it on the second call to complete the purchase; it is forwarded as the PAYMENT-SIGNATURE header, never as body data. Nothing is charged for the 402 itself, and a call that fails after payment settles nothing.

Output Schema

TableJSON Schema

Name	Required	Description
`asOf`	Yes	ISO time the upstream data was read
`coin`	Yes	The coin asked for, as the venue names it; null when listing the most-traded markets
`note`	Yes	How to read the numbers, and their limits
`venue`	Yes	The venue the markets are on (Hyperliquid)
`source`	Yes	Where the data came from
`markets`	Yes	One market when a coin was named; otherwise the most-traded by 24h volume
`crossVenueFunding`	Yes	The same coin's NEXT funding on Binance and Bybit (and Hyperliquid), as Hyperliquid publishes it

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 4, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only cover read-only/idempotent/open-world, and the description adds substantial behavioral context beyond them: paid at $0.001 USDC via x402, a 402 challenge without payment, 404 with nearest names for unknown coins, and that any >=400 answer is not charged. It also discloses the two-call payment handshake and that nothing settles on post-payment failure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but front-loaded, leading with the paid/x402 fact and the returned fields before drilling into edge cases. Slightly redundant with the title's '$0.001' and a long final sentence, but nearly every clause carries operational value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a paid, no-required-param tool with full schema coverage, an output schema, and safety annotations, the description covers everything an agent needs: data returned, default behavior, payment flow, and failure semantics. Nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: the Hyperliquid coin naming convention (kPEPE-style), the 24h-volume default when coin is omitted, and the correct payment sequencing (omit payment on the first call, send it on the second). These go beyond what the schema alone states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (Hyperliquid perpetual futures) and enumerates the exact fields returned (mark, oracle, mid price, 24h change, funding rate + APR, open interest, volume, max leverage). It is clearly distinguishable from the spot-oriented token_price sibling, and the cross-venue funding comparison is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear usage context: omit coin for the most-traded markets by 24h volume, and pass a named coin to also get next funding on Binance/Bybit for cross-venue comparison. It does not name a sibling alternative to use instead for spot prices, but the when-to-use conditions are explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All FiatDock tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.