Stillos Edge Gate

io.github.stillmarcus24Published by GitHub account stillmarcus24v1.3.2Updated Oct 24, 2026

Grade a track record before risking capital: REAL_EDGE/REGIME_LUCK/NEGATIVE_EV. Fail-closed.

The publisher's own server: Edge Network

VerifiedStreamable HTTPWeb executableFinanceData & Analytics

Overview

AI-generated overview

Grades a trading strategy's track record and returns one verdict — REAL_EDGE, REGIME_LUCK, NEGATIVE_EV or INSUFFICIENT_DATA — with a signed receipt.

What you can do
  • Grade a trade history and get a single verdict on whether the strategy has a real edge
  • Run a chronological out-of-sample holdout, fee and slippage adjustment, and a significance test on fee-adjusted expected value
  • Receive the verdict together with train/test splits, a t-statistic and stated reasons
  • Get a signed, independently verifiable receipt for each verdict
When to use it
Useful when you have a list of past trades for a strategy and want a quick, conservative check on whether its results survive out-of-sample testing and costs before committing capital. Also handy as a library call inside a larger evaluation workflow.
Requirements
Runs as a remote streamable HTTP endpoint or locally via npx (Node.js). No authentication, environment variables or headers are declared. Input is a JSON array of trades with timestamp, entry price between 0 and 1, side (yes/no) and outcome (1 won, 0 lost).
Before you install
The verdict is a statistical screen, not investment advice, and the README states the tool is fail-closed, so anything not clearly positive is rejected. Trade data you submit is sent to the remote endpoint if you use it. The README links to an external site for receipt verification, which you should evaluate yourself.

Installation

In SourceWeft

  1. Open Stillos Edge Gate in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.stillmarcus24%2Fstillos-edge-gate/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "stillos-edge-gate": {
      "type": "http",
      "url": "https://stillos-edge-gate-edge.stillos.workers.dev/mcp"
    }
  }
}

README

stillos-edge-gate

A callable trust primitive. Grade a track record before you commit capital.

A real edge is not a prediction — it is a repeatable, out-of-sample, fee-adjusted decision advantage that survives a regime change. This tells you, in one word, whether a strategy has one:

REAL_EDGE | REGIME_LUCK | NEGATIVE_EV | INSUFFICIENT_DATA

Fail-closed: anything that isn't a surviving, fee-adjusted, regime-stable edge is rejected. Every verdict ships with a signed, independently verifiable receipt.

Install

bash
npx stillos-edge-gate grade trades.json

or add as an MCP server (Claude Desktop / any MCP client):

json
{ "mcpServers": { "stillos-edge-gate": { "command": "npx", "args": ["stillos-edge-gate", "mcp"] } } }

Input

json
[ { "t": "2026-06-01T12:00:00Z", "price": 0.62, "side": "no", "outcome": 1 }, ... ]

price = entry price 0..1 · side = yes|no · outcome = 1 won / 0 lost.

How it decides

  • chronological 70/30 out-of-sample holdout (most-recent 30% is the test)
  • fee + slippage adjusted per trade
  • significance test (t ≥ 1.5) on fee-adjusted EV
  • REAL_EDGE only if +EV in both splits after fees, significant.

Why trust it

We ran it on our own live trading book first. It returned NEGATIVE_EV — and we published the signed receipt. We don't sell edges; we tell you whether yours is real.

Library

js
const { gradeStrategy } = require('stillos-edge-gate');const v = gradeStrategy(trades); // { verdict, train, test, t_stat, reasons }

MIT. https://nolawealthfinancial.com/notary

Source: README.md at commit dbe74d9

Tools

1

grade_strategy

Grade a trading/strategy track record BEFORE committing capital. Returns one verdict -- REAL_EDGE, REGIME_LUCK, NEGATIVE_EV, or INSUFFICIENT_DATA -- via chronological out-of-sample holdout, fee+slippage adjustment, and a significance test. Fail-closed. Includes a signed, independently verifiable receipt when reachable.

Parametersagenttradesrequired

Version history

1
  1. v1.3.2LatestSep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Edge integrations