FortFi Treasury MCP

set_hyperliquid_managed_exit

Trailing stop, break-even stop and/or time stop that FortFi keeps on an open perp position. Trailing: a stop trailingStopPct behind the best price since set, moved only toward the price, never away; a tighter stop already on the book (yours, or a copy-trade stop) is kept. With trailStartProfitPct, trailing starts only once the price is that % past your entry price. Break-even: once the price is breakEvenAtProfitPct past entry, the stop moves to the entry price. Time stop: closes the whole position after closeAfterHours; refused on accounts a strategy runs, since the strategy would reopen it. Checked every 5 minutes, so fast moves can pass the trail before it updates; the stop on the book is what protects you between checks. Each change runs through policy and the audit log. Stop moves that only tighten skip co-sign rules; if a co-sign rule would make a close wait for approval, the managed exit stops and says why. Calling again replaces the settings. Needs automated signing (Delegated Access) on human accounts.

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": {
      "walletId": "<walletId>",
      "symbol": "<symbol>"
    },
    "name": "set_hyperliquid_managed_exit"
  }
}

Input Schema

Name	Required	Description
`symbol`	Yes	Perp symbol, e.g. BTC or xyz:NVDA
`walletId`	Yes
`closeAfterHours`	No	Close the position this many hours from now. Refused on accounts a strategy runs.
`trailingStopPct`	No	Percent behind the best price
`trailStartProfitPct`	No	Start trailing only once the price is this % past the entry price. Needs trailingStopPct.
`breakEvenAtProfitPct`	No	Once the price is this % past the entry price, move the stop to the entry price

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 5, 2026

TDQS

A4.6/5.0

Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so thoroughly: 5-minute check cadence and the resulting gap risk, the fact that the on-book stop is what protects between checks, that trailing moves only toward price and never widens an existing tighter stop, that each change goes through policy and audit log, that tightening-only moves skip co-sign rules, and that the exit halts if a co-sign rule would delay a close.

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?

Front-loaded with the core purpose and every sentence carries information about behavior the agent cannot get elsewhere. It is delivered as one dense block rather than being segmented by mechanism, which makes the trailing/break-even/time-stop boundaries harder to scan than they need to be.

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 6-parameter mutation tool with no annotations and no output schema, the description covers the safety profile, cadence, refusal conditions, prerequisite signing, idempotency, and co-sign interaction. An agent has everything needed to call it correctly or recognize when it would be rejected.

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 already 83%, so the schema baseline is 3. The description adds genuine semantics on top: trailingStopPct only ratchets toward price, trailStartProfitPct gates when trailing begins and depends on trailingStopPct, and breakEvenAtProfitPct moves the stop to entry rather than an arbitrary price.

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 first sentence names the specific resource (managed exit on an open perp position) and the three mechanisms it manages (trailing, break-even, time stop). 'Calling again replaces the settings' pins down that this is a setter with upsert semantics, distinguishing it from list_hyperliquid_managed_exits and cancel_hyperliquid_managed_exit without naming them.

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?

It gives clear preconditions and exclusions: 'Refused on accounts a strategy runs' and 'Needs automated signing (Delegated Access) on human accounts', plus the replace-on-recall behavior. What it never does is name a sibling alternative explicitly (cancel_hyperliquid_managed_exit, list_hyperliquid_managed_exits), so the agent must infer routing.

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

All FortFi Treasury MCP 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.

Resources

Need Help?