Varrd

Name: Varrd
Author: augiemazza

@augiemazza

About Varrd

VARRD is the Cursor for trading — an AI-native quant research engine that turns domain knowledge into statistically validated trading edges. Describe any idea in plain English, and VARRD loads real market data, builds the pattern, and runs institutional-grade statistical tests to

#trading #backtesting #finance #edges #quant #systems #algorithms #markets #stocks #crypto #futures #daytrading #investing

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "augiemazza-varrd": {
      "args": [],
      "command": "varrd"
    }
  }
}

Tools

Free

~20-30c

Overview

What is Varrd?

Varrd is a quantitative research system that tests trading strategies using institutional-grade statistical bias correction and penalty enforcement. It converts plain‑English trading ideas into rigorous edge verdicts (edge or no edge) with exact entry, stop‑loss, and take‑profit prices.

How to use Varrd?

Install via pip install varrd, then use the Python library or CLI tool. For AI agents (Claude Desktop, Claude Code, Cursor), add the MCP server configuration with transport type streamable-http pointing to https://app.varrd.com/mcp. Typical workflow: varrd scan to see current signals, then varrd research "your idea" for a multi‑turn statistical test.

Key features of Varrd

Scans live strategies for actionable signals (free)
Researches trading ideas via multi‑turn AI workflow (~20–30¢)
Discovers edges autonomously (~20–30¢)
Enforces statistical guardrails (K‑penalty, multiple testing correction)
Supports futures (CME), US equities, and crypto (Binance)
Provides exact entry, stop‑loss, and take‑profit prices

Use cases of Varrd

Backtest a plain‑English trading idea to see if it has genuine edge
Scan saved strategies for current firing signals in real time
Discover new mean‑reversion or momentum patterns on futures
Link an AI agent to the web dashboard for cross‑device strategy management

FAQ from Varrd

What statistical corrections does Varrd apply automatically?

Varrd applies K‑penalty for multiple tests, market‑drift baseline comparison, out‑of‑sample protection, and correction for observation quantity – all enforced invisibly by the system’s structure.

How do I get started with Varrd?

First use auto‑creates a free account and saves a passkey to ~/.varrd/credentials with free credits. You can then run varrd scan or varrd research immediately.

What data and timeframes does Varrd cover?

Futures (CME: ES, NQ, CL, GC, etc.) at 1h+; US equities daily; crypto (Binance: BTC, ETH, SOL etc.) at 10min+.

What is the Varrd research flow?

Your plain‑English idea → chart pattern → you approve → statistical test (event study/backtest with proper controls) → edge verdict (STRONG EDGE, MARGINAL, or NO EDGE) → exact trade setup (entry, stop, take‑profit).

Does Varrd integrate with MCP clients?

Yes. It uses streamable-http transport. Add "url": "https://app.varrd.com/mcp" to your MCP config – no further setup needed.

Comments

More Data & Analytics MCP servers

Bright Data MCP

brightdata

A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.

2.5K

MCP Deep Web Research Server (v0.3.0)

qpd-v

Enhanced MCP server for deep web research

Google Ads MCP

cohnen

An MCP tool that connects Google Ads with Claude AI/Cursor and others, allowing you to analyze your advertising data through natural language conversations. This integration gives you access to campaign information, performance metrics, keyword analytics, and ad management—all th

657