Ironflow: Hyperliquid data

Delete Ironbox

delete_ironbox

DestructiveIdempotent

Stop and delete one Ironbox from this API key's account; the agent in it stops running on Hyperliquid.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "id": "<id>"
    },
    "name": "delete_ironbox"
  }
}

Input Schema

Name	Required	Description	Default
`id`	Yes	Ironbox id (ibx_...) from list_ironboxes

Output Schema

Name	Required	Description
`id`	No	Ironbox id (ibx_...)
`url`	No	This Ironbox in the API
`mode`	No	paper (simulated funds) or live
`name`	No	Name
`size`	No	small, medium or large
`paper`	No	True on a paper box: the agent's own simulated Hyperliquid account
`state`	No	creating, running, stopped, deleted or error
`trial`	No	True on a keyless trial box
`notice`	No	Present when the API added a note: how a market name was read, that data starts later than asked because of the history window, or a next step such as a free key
`region`	No	Where it runs, e.g. tokyo
`markets`	No	Markets the agent trades: perps, outcomes, spot
`message`	No	What happens next, from the API
`runtime`	No	python or node
`snippet`	No	A first Python program for this box. Shown only when created or rotated
`base_url`	No	Set the Hyperliquid SDK's base_url to this. Shown only when a paper box is created or rotated
`dashboard`	No	Where the user manages it on ironflow.sh
`created_at`	No	Creation time, Unix milliseconds
`expires_at`	No	When a trial box ends at the latest, Unix milliseconds
`activity_url`	No	Where to watch this box. Shown only with base_url
`strategies_url`	No	Where to start strategies on this box. Shown only with base_url
`starting_balance_usd`	No	Starting balance of a new paper box

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 8, 2026

addedOutput schema / properties / activity_url

Added value: +{
+  "description": "Where to watch this box. Shown only with base_url"
+}

changedOutput schema / properties / expires_at / description

Previous value: -"When a trial box ends and is removed, Unix milliseconds"New value: +"When a trial box ends at the latest, Unix milliseconds"

addedOutput schema / properties / strategies_url

Added value: +{
+  "description": "Where to start strategies on this box. Shown only with base_url"
+}

Changed6 schema fields changedNov 8, 2026

addedOutput schema / properties / base_url

Added value: +{
+  "description": "Set the Hyperliquid SDK's base_url to this. Shown only when a paper box is created or rotated"
+}

addedOutput schema / properties / expires_at

Added value: +{
+  "description": "When a trial box ends and is removed, Unix milliseconds"
+}

addedOutput schema / properties / paper

Added value: +{
+  "description": "True on a paper box: the agent's own simulated Hyperliquid account"
+}

addedOutput schema / properties / snippet

Added value: +{
+  "description": "A first Python program for this box. Shown only when created or rotated"
+}

addedOutput schema / properties / starting_balance_usd

Added value: +{
+  "description": "Starting balance of a new paper box"
+}

addedOutput schema / properties / trial

Added value: +{
+  "description": "True on a keyless trial box"
+}

AddedNov 7, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds real consequence beyond that: the running agent inside the Ironbox ceases to execute on Hyperliquid, which is exactly the outcome an agent needs before committing to a destructive call.

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?

One compact sentence with the destructive action front-loaded and the operational consequence attached after the semicolon. No redundant or filler wording.

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?

An output schema exists and annotations cover safety, so the description only needs the action and consequence, both of which are present. A slightly fuller definition would note irreversibility and whether dependent strategies or alerts tied to the Ironbox are also removed.

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 coverage is 100% and the single 'id' parameter is documented with the ibx_... prefix and a pointer to list_ironboxes. The description adds nothing about the parameter, so the baseline 3 applies.

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

Purpose4/5

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

States a specific verb ('stop and delete') and resource ('one Ironbox') with a clear scope ('this API key's account'), which separates it from get_ironbox, list_ironboxes, and create_ironbox. It stops short of naming a sibling explicitly, but the action is unambiguous.

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?

The description implies a teardown scenario but offers no explicit when-to-use vs. when-not guidance, nor does it point to alternatives such as stop_box_strategy for pausing rather than deleting. The 'stop' wording implies the delete also halts the agent, but that is inferred, not spelled out.

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

All Ironflow: Hyperliquid data 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.