Skip to main content
Glama
kitsune-de

hyperliquid-mcp

by kitsune-de
OverviewSchemaRelated ServersScoreDiscussions
TypeScript

hyperliquid-mcp

Give your AI agent eyes on Hyperliquid. A tiny, read-only MCP server that lets Claude (or any MCP-compatible agent) query Hyperliquid perp markets, funding rates, order books, candles — and the positions, fills and funding of any address.

  • 🔑 No API keys, no wallets, no signing — only the public Info API. It cannot trade, ever.

  • 📦 Zero config — one entry in your MCP config and you're done.

  • 🪶 Tiny — two source files, two dependencies (MCP SDK + zod).

Quick start

Claude Code

claude mcp add hyperliquid -- npx -y @kitsune-de/hyperliquid-mcp

Claude Desktop / Cursor / any MCP client

{
  "mcpServers": {
    "hyperliquid": {
      "command": "npx",
      "args": ["-y", "@kitsune-de/hyperliquid-mcp"]
    }
  }
}

From source

git clone https://github.com/kitsune-de/hyperliquid-mcp
cd hyperliquid-mcp && npm install && npm run build
# then point your MCP client at: node /path/to/hyperliquid-mcp/dist/index.js

Related MCP server: 0xarchive-mcp

What you can ask

"What are the most extreme funding rates on Hyperliquid right now?"

"Show the open positions and liquidation prices of 0xabc… — how close is it to liquidation?"

"How much funding did my account pay over the last week, per coin?"

"Pull 4h candles for HYPE and describe the trend."

Tools

Tool

Arguments

Returns

get_markets

coin?, sortBy? (volume · funding · change · openInterest), limit?

Perp markets: mark price, 24h change & volume, open interest, funding (1h + annualized APR), max leverage

get_price

coins?

Mid prices for given coins, or all perp mids

get_orderbook

coin, depth?

L2 snapshot: best bid/ask, spread %, levels per side

get_candles

coin, interval?, count?

OHLCV candles (1m … 1w)

get_account

address

Account value, margin usage, withdrawable, every perp position (side, size, entry, liq price, uPnL, leverage), spot balances

get_open_orders

address

Resting orders: side, price, size, type, trigger info

get_recent_fills

address, limit?

Recent fills: direction, price, size, notional, closed PnL, fees

get_funding_paid

address, hours?

Net funding paid/received per coin over a window

All account tools work on any address — your own, a whale's, a vault's. It's all public on-chain data.

Configuration

Env var

Default

Purpose

HL_INFO_URL

https://api.hyperliquid.xyz/info

Set to https://api.hyperliquid-testnet.xyz/info for testnet

Development

npm install
npm run build
npm run smoke   # spawns the server over stdio and exercises every tool against live mainnet

Disclaimer

Read-only market data tooling. Not financial advice; no affiliation with Hyperliquid.

License

MIT

Available Tools

2 tools
get_funding_paidFunding paid/receivedA

Net funding paid or received by an address over the last N hours, broken down by coin. Positive = received, negative = paid.

ParametersJSON Schema
NameRequiredDescriptionDefault
hoursNoLookback window in hours (default 24)
addressYesEVM address of the Hyperliquid account, e.g. 0xdfc24b077bc1425ad1dea75bcb6f8158e10df303

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description discloses the tool returns net funding over a configurable period, broken down by coin, and explains the sign. It is read-only, non-destructive, and transparent about the data scope.

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

Conciseness5/5

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

Single sentence, highly concise, front-loads the core function and unique details without extraneous text.

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

Completeness3/5

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

Given no output schema, the description hints at a breakdown by coin but doesn't specify the return format (e.g., list of objects, single value). Adequate for a simple tool but could be more explicit about output structure.

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 covers both parameters with descriptions. The description adds the sign convention and confirms the breakdown by coin, which enhances understanding beyond the schema.

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?

Description clearly states the tool retrieves net funding paid/received by an address, specifies the sign convention (positive=received, negative=paid), and distinguishes from sibling 'get_open_orders' which deals with orders.

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

Usage Guidelines3/5

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

No explicit guidance on when to use or not use this tool versus alternatives like 'get_open_orders'. The context is implied but not directly stated.

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

get_open_ordersOpen ordersA

Resting open orders for an address: side, price, size, order type, trigger info.

ParametersJSON Schema
NameRequiredDescriptionDefault
addressYesEVM address of the Hyperliquid account, e.g. 0xdfc24b077bc1425ad1dea75bcb6f8158e10df303

TDQS

A4/5.0
Behavior3/5

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

The description discloses that the tool returns specific order details, implying a read-only operation. However, it does not mention authentication requirements, rate limits, or any behavior when the address is invalid, and no annotations are provided to fill the gap.

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

Conciseness5/5

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

The description is a single sentence that immediately conveys the tool's purpose and return fields. No unnecessary words, and the information is front-loaded.

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

Completeness4/5

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

Given the tool's simplicity (single parameter, no output schema), the description covers the core functionality and expected return fields. It could be improved by mentioning potential errors or address validation, but it is largely complete for typical use.

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

Parameters3/5

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

Schema description coverage is 100%, and the schema already describes the 'address' parameter adequately. The description does not add additional semantic meaning about the parameter beyond what the schema provides.

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?

The description clearly states the tool returns 'resting open orders' for a given address, including specific fields (side, price, size, order type, trigger info). This distinguishes it from the sibling tool 'get_funding_paid', which serves a different purpose.

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?

The description implicitly indicates when to use it (when you need open orders for an address) but does not explicitly state when not to use it or compare it to alternatives. However, the only sibling is unrelated, so confusion is minimal.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 2 tool updatesv0.1.0
    • First observedget_funding_paid
    • First observedget_open_orders
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.9/5.0
Disambiguation5/5

The two tools address completely different aspects: one provides open orders, the other provides funding history. There is no overlap or ambiguity.

Naming Consistency5/5

Both tools follow a consistent 'get_<noun>' pattern, making the naming predictable and clear.

Tool Count2/5

With only 2 tools, the server feels very thin for a trading platform. Typically one would expect many more operations like placing/canceling orders, getting positions, etc.

Completeness1/5

The server lacks essential operations such as placing, canceling, or modifying orders, as well as getting account balances or positions. The limited surface cannot support meaningful trading workflows.

Maintenance

ActivitySlowing
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • 0xarchive-mcp

    0xArchiveIO
    A
    license
    A
    quality
    F
    maintenance
    MCP server for querying historical and real-time crypto market data across Hyperliquid, Hyperliquid HIP-3, and Lighter.xyz - orderbooks, trades, candles, funding, open interest, liquidations, and data quality metrics.
    100
    27
    11
    MIT

  • hl-read

    akagifreeez
    A
    license
    Not graded
    quality
    B
    maintenance
    A read-only MCP server for Hyperliquid that provides public market data (prices, order books, funding) and any wallet's positions, orders, and fills via MCP tools, without requiring a private key.
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/kitsune-de/hyperliquid-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server