FortFi Treasury MCP

start_copy_trade

Copy another Hyperliquid account on one of your wallets. Every hour FortFi reads their book, keeps their largest positions until 95% of their exposure is covered (at most 10 names), scales to your equity and leverage cap, and trades only when a position drifts more than 10% from target. Leverage cap 1 or 2; 3 and 5 are high risk and need acceptHighRisk: true. Same rails, caps and key re-checks as start_strategy.

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>",
      "address": "<address>",
      "leverage": "<leverage>"
    },
    "name": "start_copy_trade"
  }
}

Input Schema

Name	Required	Description
`address`	Yes	0x address to copy
`leverage`	Yes	Leverage cap: 1, 2, 3 or 5 (3 and 5 need acceptHighRisk)
`walletId`	Yes	hyperliquid-mainnet wallet id
`maxLossPct`	No	Optional loss cap, whole percent (1-90). If the strategy's P&L since start falls this far below the money it runs on, FortFi stops it and closes its positions. Checked every 5 minutes.
`acceptHighRisk`	No	Required for a 3x or 5x cap: you accept it can lose most of the money in this wallet.
`maxAllocationUsd`	No	Optional cap on equity used, e.g. "500"

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 3, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations, the description carries the behavioral burden and does well: hourly cadence, the 95%-exposure/10-name selection rule, equity- and leverage-cap scaling, and the 10% drift tolerance all disclose how the tool will actually trade. It falls short on what a run returns, what happens to already-open positions or an existing copy trade on the same wallet, and the vague 'same rails, caps and key re-checks as start_strategy' leaves the risk controls under-defined.

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 purpose, then mechanics, then the leverage constraint — good ordering with no filler sentences. The mechanics sentence is dense but each clause carries information; only the trailing 'same rails... as start_strategy' is low-value shorthand.

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 annotations, no output schema, and six parameters, the description should say what is returned (strategy id?) and how the copy trade is later inspected or stopped. It covers ongoing behavior well but leaves the invocation result and lifecycle underspecified.

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%, so all six parameters — including the nuanced maxLossPct semantics and the acceptHighRisk enum — are already fully documented in the schema. The description's leverage/high-risk sentence largely restates the schema's leverage description and says nothing about maxAllocationUsd or maxLossPct, so the baseline of 3 is right.

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 opening sentence names a specific verb and resource (copy another Hyperliquid account) plus the scope (on one of your wallets), and the rest of the sentence spells out the replication mechanism, which separates it cleanly from start_strategy and the read-only copy-trade siblings (get_copy_trade_wallet, list_copy_trade_leaders).

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 clearly implies when to use it (replicating another account's book) and adds an enforced eligibility rule: leverage 1 or 2 is normal, 3 and 5 require acceptHighRisk: true. There is no explicit 'do not use this if...' or pointer to list_copy_trade_leaders for finding an address, so exclusions/alternatives are only partial.

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?