strategy-lab

MCP serverDev tools

strategy-lab lets your AI stress-test trading strategies for lowcaps, perpetuals, and liquidity pools. After each run it returns the full distribution of outcomes plus a reproduction seed, so results can be checked and repeated.

Use strategy-lab in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add strategy-lab and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use strategy-lab to get agent state

Details

Available today. Use it from your connected AI after setup.

Add strategy-lab, then ask your AI to stress-test a strategy and walk through the returned distribution.

strategy-labStart free

What your AI can do with it

  • Stress-test lowcap trading strategies
  • Stress-test perpetual strategies
  • Stress-test liquidity pool strategies
  • See the full distribution of outcomes for each test
  • Get a reproduction seed so any run can be repeated

Install strategy-lab

The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user strategy-lab 'https://kellyruns.xyz/mcp'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://kellyruns.xyz/mcp

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=strategy-lab&config=eyJ1cmwiOiJodHRwczovL2tlbGx5cnVucy54eXovbWNwIn0=

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://kellyruns.xyz/mcp

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add strategy-lab --url 'https://kellyruns.xyz/mcp'

    Run it once, then sign in with codex mcp login strategy-lab if the server asks for an account.

From the project's README

As published by kellyruns/kellyruns in README.md.

kellyruns.xyz · how it works · @KellyRunsIt

◢ whoami

const kelly = {
  what:      "autonomous trading agent that shows its work",
  chain:     "Robinhood Chain · 4663 · Arbitrum stack",
  loop:      ["observe", "think", "decide", "act", "learn", "broadcast"],
  publishes: "the reasoning behind every call — including the losing ones",
  ledger:    "append-only. failures and rules-engine rejections included",
  execution: "paper mode. the EVM path is wired and deliberately not armed",
  thesis:    "nobody pays to be wrong",
} as const;

◢ the strategy lab

Most people learn leverage, liquidation and impermanent loss by losing money to them. The lab is the cheaper way round.

You submit a lowcap, perp or LP strategy as parameters, not prose. The lab stress-tests it across thousands of simulated paths and publishes the whole distribution — not one backtest number that hides the tail where the damage lives.

Certification gate≥ 3 runs and ≥ 1,500 paths
How to sizeagainst the 5th percentile the run prints, never the median
What a pass meansa statement about a distribution — not a prediction
Who paystrading fees cover the $0.85 of compute per run. Not you.

◢ connect an agent

Kelly speaks MCP, so another agent can read the record without scraping HTML — and the reproduction seed comes with it.

claude mcp add --transport http kelly https://kellyruns.xyz/mcp

Stateless streamable HTTP, protocol 2025-06-18, no auth and no key. Published to the official registry as xyz.kellyruns/strategy-lab.

Read-only by design. No tool here submits a strategy, funds a run, or moves anything — writes belong behind a wallet session, and an unauthenticated endpoint is the wrong place to re-implement one.

Tools

ToolWhat it returns
get_agent_stateTreasury, open positions, recent trades, and the reasoning behind the latest cycle. Paper mode — a published track record, not a portfolio.
get_certification_gateThe thresholds a strategy must clear, and what a pass does and does not mean. Read this first.
get_lab_summaryCounts by status, testing-pool balance, and how many runs it can still fund.
list_strategiesStrategies filtered by kind and status, each with its certification rollup — runs, paths, median PnL, worst case, ruin rate.
get_strategyOne strategy in full: parameters, verdict, every check the gate ran, and each run's PRNG seed.

The seed is the point. Re-running with it reproduces the result exactly, which is what makes a verdict something you can disagree with by running it rather than by arguing about it.

◢ why "Kelly"

The Kelly Criterion (John L. Kelly Jr., Bell Labs, 1956) answers the question retail traders skip: not is this a good bet but how much should I bet. That is the direct ancestor of the risk clamp that gets the last word on sizing here, over anything the model proposed.

Which is also why the agent is a character and not a dashboard. Kelly says no is a sentence. A tool can't be the subject of one.

◢ honest status

Up front, because a project about publishing losses cannot be coy about its own readiness.

execution   paper mode. every fill simulated, slippage and fees modelled
            pessimistically so edge isn't an artifact of frictionless fills
evm path    wired, deliberately NOT armed — pending real quoting, bounded
            approvals, a token safety check, and nonce management
vault       no contract deployed. /vault shows a requirements checklist,
            not a deposit button. nothing here custodies anyone's funds
wallet      connecting signs an identity statement and nothing else.
            no transaction, no approval, no transfer
advice      none of this is financial advice. the agent is not a licensed
            advisor, and a certification is not a prediction

◢ on chain

ChainRobinhood Chain — 4663, Arbitrum stack, ETH gas
ERC-8004 Identity Registry0x8004A169…a432
Agent registration/.well-known/agent-registration.json

◢ built with

TypeScript · Next.js · viem · Postgres · Anthropic SDK

The art above is generated by scripts/build-art.mjs — two self-contained SVGs, no external fonts and no remote assets, because GitHub's image proxy blocks every outbound fetch. No third-party widget services either, so nothing here breaks when someone else's server goes down.


Built on Robinhood Chain. Not affiliated with, endorsed by, sponsored by, or partnered with Robinhood Markets, Inc. The chain is permissionless — anyone can deploy on it without approval, and that includes this project.

Tools it offers (5)

What this server listed when Ahel dialed its public endpoint in Oct 2026, with no key and no account of yours. The names are the server’s own.

  • get_agent_state
  • get_certification_gate
  • get_lab_summary
  • list_strategies
  • get_strategy

Signals

Last commit
Aug 2026
Advanced
Delivery
strategy-lab MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
xyz-kellyruns-strategy-lab
Source
github.com/kellyruns/kellyruns
Hosted endpoint
https://kellyruns.xyz/mcp