stillos-edge-gate
Grades prediction market trade logs to determine if a strategy has a statistically significant, fee-adjusted edge using out-of-sample holdout, returning a signed verdict.
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
npx stillos-edge-gate grade trades.json
or add as an MCP server (Claude Desktop / any MCP client):
{ "mcpServers": { "stillos-edge-gate": { "command": "npx", "args": ["stillos-edge-gate", "mcp"] } } }
Input
[ { "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_EDGEonly 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
const { gradeStrategy } = require('stillos-edge-gate');
const v = gradeStrategy(trades); // { verdict, train, test, t_stat, reasons }
MIT. https://nolawealthfinancial.com/notary
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.