# varrd [Health: Active]

**Category:** 💰 Finance & Fintech  
**Repository:** https://github.com/augiemazza/varrd  
**GitHub Stars:** 24  
**Views:** 3  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/varrd

## Description
Validated quant research. Test trading ideas with real data and statistical guardrails.

## Tools
Capabilities this server exposes over MCP:

- **varrd_edges** — THE PRIMARY TOOL — start here. FREE at depth=0, always safe to call.

Live feed of THIS USER'S OWN statistically validated trading edges — the ones on their account — running 24/7 against real market data. See which of YOUR edges are firing right now, get trade levels, or audit the full methodology. Scoped to the connected account: if the user has no edges yet, this returns none (it is NOT a general/shared library).

THREE TIERS:
  depth=0 (FREE — call this first): See which of YOUR edges are firing right now, pending bar close, or actively in trades. Markets and status only — no direction, no stats. Get a sense of what's live.
  depth=1 ($0.50): Unlock direction, occurrence count, EV/trade, stop-loss, take-profit, hold horizon, and current entry prices for ALL active edges in one request.
  depth=2 ($1 per edge, $5 for all): Full methodology — the actual formula, setup code, how the edge was discovered, edge decay analysis, complete performance analytics (Sharpe, drawdown, equity curve, profit factor). Machine-readable so any AI can audit the statistical rigor. Includes drill-down sections (free after purchase): setup_code, horizons, analytics, occurrences, and view (interactive chart link for your user, 15 min).

Every edge in this library is Bonferroni-corrected, tested against both zero returns and market baseline, with K-tracking to prevent p-hacking. Out-of-sample validated. Full transparency.
- **varrd_ai** — Talk to VARRD AI (~$0.25/turn). Describe any trading idea in plain language and the system handles everything — loading decades of market data, charting your pattern, running statistical tests, backtesting with stops, and generating exact trade setups.

MULTI-TURN: First call creates a session. Keep calling with the same session_id, following context.next_actions each time.
  1. Your idea -> VARRD charts pattern
  2. 'test it' -> statistical test (event study or backtest)
  3. 'show me the trade setup' -> exact entry/stop/target prices

HYPOTHESIS INTEGRITY (critical):
VARRD tests ONE hypothesis at a time — one formula, one setup. Never combine multiple setups into one formula or ask to 'test all' — each idea must be tested as a separate hypothesis for the statistics to be valid. Say 'start a new hypothesis' between ideas to reset cleanly.
  - ALLOWED: Test the SAME setup across multiple markets ('test this on ES, NQ, and CL') — same formula, different data.
  - NOT ALLOWED: Test multiple DIFFERENT formulas/setups at once — each is a separate hypothesis requiring its own chart-test-result cycle.
If ELROND council returns 4 setups, test each one separately: chart setup 1 -> test -> results -> 'start new hypothesis' -> chart setup 2 -> etc.

KEY CAPABILITIES you can ask for:
  - 'Use the ELROND council on [market]' -> 8 expert investigators
  - 'Optimize the stop loss and take profit' -> SL/TP grid search
  - 'Test this on ES, NQ, and CL' -> multi-market testing
  - 'Simulate trading this with 1.5 ATR stop' -> backtest with stops

EDGE VERDICTS in context.edge_verdict after testing:
  - STRONG EDGE: Significant vs zero AND vs market baseline
  - MARGINAL: Significant vs zero only (beats nothing, but real signal)
  - PINNED: Significant vs market only (flat returns but different from market)
  - NO EDGE: Neither significant test passed

TERMINAL STATES: Stop when context.has_edge is true (edge found) or false (no edge — valid result). Always read context.next_actions.
- **search** — Search your saved hypotheses by keyword or natural language query. Returns matching strategies ranked by relevance, with key stats (win rate, Sharpe, edge status). Use this to find strategies you've already validated.
- **get_hypothesis** — Get full detail for a specific hypothesis/strategy. Returns formula, entry/exit rules, direction, performance metrics (win rate, Sharpe, profit factor, max drawdown), version history, and trade levels. Everything an agent needs to understand and act on a strategy.
- **check_balance** — Check your credit balance and see available credit packs. Free — no credits consumed. Also auto-detects completed payments — call this after your user pays via a checkout link to confirm credits were added. If payment went through, the response includes recovered_cents.
- **buy_credits** — Buy credits for the edge library and AI research. Default $5 minimum. Free — no credits consumed to call this.

TWO PAYMENT METHODS:
  card (default): Returns a Stripe Checkout link for your user to click and pay. After payment, call check_balance to confirm credits were added.
  crypto: USDC on Base. Fully autonomous — no human needed. Three steps:
    1. buy_credits(payment_method='crypto') → returns deposit address + payment_intent_id
    2. Send USDC to the deposit address (use your wallet tool)
    3. buy_credits(payment_intent_id='pi_...') → confirms payment, credits added instantly
  If you have wallet access, this is the fastest path — fully machine-to-machine.
- **reset_session** — Kill a broken research session and start fresh. Use this when a session gets stuck, produces errors, or enters a bad state. Free — no credits consumed. After resetting, call research without a session_id to start a new clean session.
- **autonomous_varrd_ai** — Point VARRD's autonomous AI in a direction and let it discover edges for you. Give it a topic and it draws from one of the most comprehensive market structure knowledge graphs ever built — containing ideologies and theories, not statistics — so it generates genuinely novel hypotheses rather than overfitting to what already worked.

BEST FOR: Exploring a space broadly. Give it 'momentum on grains' and it might test wheat seasonal patterns, corn spread reversals, or soybean crush ratio momentum. It propagates from your seed idea into related concepts you might not think of.

Returns a complete result — edge or no edge, stats, trade setup. Each call tests ONE hypothesis through the full pipeline (~$0.25/idea). Call again for another idea.

Use 'varrd_ai' instead when YOU have a specific idea to test and want full control over each step.
- **get_briefed** — Get a personalized market news briefing based on your validated edge library. Profiles your strategies, searches today's news for the instruments and setups you actually trade, and writes a concise digest connecting each headline to your specific book.

Each news item includes a ↳ line tying it to your actual positions and edges (e.g. 'your ES momentum setups', 'your GC mean-reversion edge').

Requires at least 5 strong edges in your library. Costs credits.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `uvx` (confidence: high):

```json
"mcpServers": {
  "varrd": {
    "command": "uvx",
    "args": ["varrd"]
  }
}
```

## Documentation

## What the varrd MCP server does

The varrd MCP server gives an MCP client access to VARRD’s account-scoped library of statistically validated trading edges and its research workflow. It can show which of the connected user’s edges are firing, pending a bar close, or already in trades. Depending on the requested depth, results may include direction, occurrence counts, expected value, stop-loss and take-profit levels, hold horizon, entry prices, formulas, setup code, discovery history, and performance analytics.

The library is not a shared catalog of strategies. Results depend on the connected account having saved edges. VARRD states that its validated edges are tested out of sample, Bonferroni-corrected, compared with both zero returns and a market baseline, and tracked for repeated testing to reduce p-hacking.

## How it works

Research begins with a plain-language idea sent to `varrd_ai`. The first call creates a session, and later calls reuse its `session_id` while following the returned `context.next_actions`. A typical sequence is to describe a setup, request a chart or pattern view, ask to test it, and then request a trade setup. The system can run event studies or backtests, test one formula across several markets, search stop-loss and take-profit combinations, and simulate stops such as an ATR-based rule.

Each research call must represent one hypothesis. Different formulas or setups need separate research cycles, while the same setup can be tested across multiple markets. Results terminate with an edge verdict such as strong edge, marginal, pinned, or no edge. The AI interprets results, but VARRD says statistical calculations are performed by a separate deterministic engine in a sandboxed kernel.

## Setup and configuration

VARRD provides a Streamable HTTP endpoint at `https://app.varrd.com/mcp`. An MCP client can connect using that URL without an API key. The README specifically lists Claude Desktop and Cursor as compatible clients; it also mentions OpenBB and other MCP clients.

The repository also documents a Python SDK installation with `pip install varrd`, but that installs the SDK rather than serving as the MCP endpoint configuration. For a hosted MCP connection, configure the endpoint directly in the client.

## Tools and capabilities

- `varrd_edges` provides free market and status information at depth 0, paid directional and trade details at depth 1, and deeper methodology and analytics at depth 2.
- `varrd_ai` supports multi-turn hypothesis development, charting, statistical testing, backtesting, and trade-setup generation.
- `autonomous_varrd_ai` explores a supplied topic by generating and testing one hypothesis per call.
- `search` finds saved hypotheses by keyword or natural-language query.
- `get_hypothesis` retrieves a strategy’s formula, rules, metrics, version history, and trade levels.
- `get_briefed` creates a personalized market-news briefing when the account has at least five strong edges.
- `check_balance`, `buy_credits`, and `reset_session` manage credits and stuck research sessions.

## Limitations and notes

Depth 0 edge status is free, while deeper edge data and research actions use credits. The documented prices include $0.50 for a depth-1 snapshot, $1 per edge or $5 for all edges at depth 2, and about $0.25 per AI research turn or autonomous hypothesis. Credit purchases can use Stripe Checkout or USDC on Base.

Live edge results are scoped to the connected account, and a new account may return no edges. `get_briefed` requires at least five strong edges. Research should stop when the returned context reports either an edge found or a valid no-edge result. If a session becomes stuck, use `reset_session` before starting a new one.

_Full upstream README: https://allmcps.com/mcp/varrd/readme_