FortFi Treasury MCP

run_hyperliquid_research_backtest_spec

Run an out-of-sample backtest from a Strategy Spec JSON (universe + rank factor or named pattern + portfolio rules). Deterministic; reads hl_research_* Postgres. Agent should translate natural-language strategy ideas into the spec object before calling. Pass presetId instead of spec to get a FortFi house preset (crypto-majors, core-momentum, mag7, semis, memory, ai-compute, pre-ipo, ...) with its frozen spec and published OOS, walk-forward, drawdown and leverage scenarios; add rerun:true to recompute it live.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

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

Input Schema

Name	Required	Description
`prod`	No	Use production Supabase (default false in dev)
`spec`	No	Strategy Spec: name, universe {dex, minDayVolumeUsd, includeCoins, excludeCoins, maxSymbols}, interval, signal {type rank\|pattern, factor\|pattern, params}, portfolio, costs, validation
`rerun`	No	With presetId, rerun the preset spec live instead of returning published stats
`presetId`	No	House preset id. Returns the spec plus published stats.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 3, 2026

TDQS

A3.8/5.0

Behavior3/5

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

No annotations are provided, so the description carries the full burden. It usefully discloses that execution is deterministic and reads hl_research_* Postgres, and it explains that presetId returns frozen specs plus published OOS, walk-forward, drawdown, and leverage scenarios while rerun recomputes live. However, it does not state authentication needs, runtime behavior, error handling, or whether rerun persists anything, leaving meaningful behavioral gaps.

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?

The description is front-loaded with the core action and is mostly free of fluff. The second sentence is long because it packs in preset examples, rerun behavior, and agent guidance, but every clause carries operational information.

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?

For a four-parameter tool with a nested spec object and no output schema, the description covers invocation paths well: spec translation, presetId lookup, and rerun behavior. It does not explain the return shape for the spec path or state that one of spec or presetId is required, which are notable gaps given the absence of an output schema.

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 the schema already documents all four parameters. The description reinforces the spec contents and the presetId-versus-spec relationship, but it adds little parameter syntax or constraint detail beyond what the schema already says; baseline 3 is appropriate when structured fields do the heavy lifting.

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?

States a specific verb and resource: run an out-of-sample backtest from a Strategy Spec JSON, with universe, signal, and portfolio rules named. The presetId path is also explicitly scoped, so an agent can distinguish this tool from the plain run_hyperliquid_research_backtest sibling and from preset listing tools.

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?

Gives clear usage context: translate natural-language strategy ideas into the spec object before calling, or pass presetId to use a FortFi house preset. It also explains rerun:true as the live recomputation option. It stops short of naming the sibling run_hyperliquid_research_backtest or stating when not to use this tool, so it is not a full 5.

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?