OMX for Hyperliquid MCP Server

by lumen-founder Your server? Claim it

local only

OMX for Hyperliquid runs on your own machine — the client starts it, so there is no endpoint to ping. 2 695 installs a week from pypi. Last commit 5 Nov 2026.

Hyperliquid execution for AI agents: limits, human approval, kill switch. Keyless demo + live paper.

Installs per day peak 2 090 · avg 89

a month agotoday

2 695

Installs / week

pypi · omx-hyperliquid

Stars

0 open issues

5 Nov 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

Today is the operative word: we check OMX for Hyperliquid every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add omx-hyperliquid-trading -- uvx omx-hyperliquid

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "omx-hyperliquid-trading": {
      "command": "uvx",
      "args": [
        "omx-hyperliquid"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.omx-hyperliquid-trading]
command = "uvx"
args = ["omx-hyperliquid"]

.cursor/mcp.json

{
  "mcpServers": {
    "omx-hyperliquid-trading": {
      "command": "uvx",
      "args": [
        "omx-hyperliquid"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "omx-hyperliquid-trading": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "omx-hyperliquid"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: OMX_CONFIG (Path to your omx.toml (from `omx init`; run `omx daemon` too). Leave empty for the keyless demo).

Alternatives to OMX for Hyperliquid

same job, measured the same way

Crypto Market Data

by zaffy18

Live crypto market data and Hyperliquid wallet reports for AI agents, paid per call with x402.

154 installs/wk 15 tools answering

Clawvault MCP Server

by andrewszk

AI agent payment security - spending limits, whitelists, and human approval.

72 installs/wk local only

hypernatt-terminal

by dialloube-research

Liquidation radar, execution context and Li.Fi swaps for AI agents. 6 MCP tools; x402 payments.

4 tools answering

Reins

by r2rlabs

Risk limits and an audit log for AI agents trading Hyperliquid, enforced outside the model.

local only

Mishmar

by mishmar-io

Risk management for trading bots and AI agents: limits, approvals and a stop on every order.

654 installs/wk local only

MCPify

by mcpify

Non-custodial Hyperliquid perp trading: live markets, account state, user-armed order execution

17 tools answering

GDEX Trading

by gemachdao

GDEX (gdex.pro) trading for AI agents: spot, perps and HyperLiquid on Solana, EVM and more chains

975 installs/wk local only

Coinversaa

by coinversaa

Crypto intelligence for AI agents. Hyperliquid trader analytics, cohorts, and live market data.

65 installs/wk local only

OMX for Hyperliquid — questions

Answers built from our own checks of this server.

Why is there no uptime for OMX for Hyperliquid?

OMX for Hyperliquid runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package omx-hyperliquid was installed 2 695 times last week.

How do I connect OMX for Hyperliquid?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls omx-hyperliquid straight from pypi; nothing to host, nothing to sign up for.

How many people use OMX for Hyperliquid?

The pypi package omx-hyperliquid was installed 2 695 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is OMX for Hyperliquid open source?

Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.