VARRD — Statistically Validated Trading Edges + AI Research Engine
REMOTE · APP.VARRD.COM
Validated trading edges across futures, equities, crypto. Live signals, full audit trail.
Available components
Last scanned (21 hours ago)
Scores higher than 74% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Finance and Payments
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (reset_session). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability72
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 6235 tokens (~479/item across 13 items; 11 tools + 2 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (91% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 19 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “autonomous_varrd_ai” rewrote its description, which is the text the model reads security
- Tool “buy_credits” rewrote its description, which is the text the model reads security
- Tool “prediction_ai” rewrote its description, which is the text the model reads security
- Tool “varrd_ai” rewrote its description, which is the text the model reads security
- Tool “varrd_edges” rewrote its description, which is the text the model reads security
- “varrd_edges” reworded the description of “depth” cosmetic
- “varrd_edges” reworded the description of “section” cosmetic
- 15 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “autonomous_varrd_ai” rewrote its description, which is the text the model reads security
- Tool “get_briefed” rewrote its description, which is the text the model reads security
- Tool “varrd_ai” rewrote its description, which is the text the model reads security
- “autonomous_varrd_ai” reworded the description of “markets” cosmetic
- “autonomous_varrd_ai” reworded the description of “topic” cosmetic
- “varrd_edges” reworded the description of “market” cosmetic
- 14 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “autonomous_varrd_ai” rewrote its description, which is the text the model reads security
- Tool “varrd_ai” rewrote its description, which is the text the model reads security
- Schema quality: 536 → 481 ▲ functional
- Server version: 1.0.5 → 1.1.0 functional
- New tool “prediction_ai” functional
- New tool “prediction_edges” functional
- 6 Nov 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 3 Sept 26 0
- “get_hypothesis” reworded the description of “hypothesis_id” cosmetic
1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://app.varrd.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=app.varrd.com | CN=Amazon RSA 2048 M01,O=Amazon,C=US | 5 Jan 2026 | 3 Feb 2027 | RSA 2048 | SHA256-RSA | 839237db652b06743a3157ac0bb20a4 |
| SANs: app.varrd.com | ||||||
| CN=Amazon RSA 2048 M01,O=Amazon,C=US (CA) | CN=Amazon Root CA 1,O=Amazon,C=US | 23 Aug 2022 | 23 Aug 2030 | RSA 2048 | SHA256-RSA | 77312380b9d6688a33b1ed9bf9ccda68e0e0f |
| CN=Amazon Root CA 1,O=Amazon,C=US (CA) | CN=Starfield Services Root Certificate Authority - G2,O=Starfield Technologies\, Inc.,L=Scottsdale,ST=Arizona,C=US | 25 May 2015 | 31 Dec 2037 | RSA 2048 | SHA256-RSA | 67f944a2a27cdf3fac2ae2b01f908eeb9c4c6 |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of app.varrd.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| varrd.com. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://app.varrd.com/mcp | Verified | 200 | |
| http (plaintext) | http://app.varrd.com/mcp | HTTPS enforced | 301 | https://app.varrd.com/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
autonomous_varrd_ai ~340
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 in energy stocks' and it might test refiner seasonality, oil-services breakouts, or the energy-to-utilities ratio's 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 (charged for what the run cost). Call again for another idea. Use 'varrd_ai' instead when YOU have a specific idea to test and want full control over each step.
| Name | Type | Req | Description |
|---|---|---|---|
| asset_classes | array | – | Limit to specific asset classes. Default: all. |
| context | array | – | Prior conversation context — recent user queries to use as research inspiration. Optional. |
| markets | array | – | Focus on specific markets (e.g. ['SPY', 'QQQ']). Omit for VARRD to choose. |
| search_mode | string | – | focused = stay close to topic. explore = creative freedom. Default: focused. |
| test_type | string | – | Type of statistical test. Default: event_study. |
| topic | string | yes | Research topic or trading idea (e.g. 'BTC 240min short setups', 'momentum in energy stocks', 'mean reversion after VIX spikes'). |
| Name | Type | Req | Description |
|---|---|---|---|
| context | object | – | has_edge, edge_verdict, workflow_state |
| session_id | string | – | – |
| text | string | – | Full research result with edge verdict |
| widgets | array | – | Chart, test results, trade setup |
No examples provided.
buy_credits ~249
Buy credits for 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.
| Name | Type | Req | Description |
|---|---|---|---|
| amount_cents | integer | – | Amount in cents (default 500 = $5.00). Minimum $5. |
| payment_intent_id | string | – | For crypto: Stripe PaymentIntent ID from a previous buy_credits call. Pass after sending USDC to confirm. |
| payment_method | string | – | Payment method: 'card' (default, Stripe Checkout) or 'crypto' (USDC on Base). |
| Name | Type | Req | Description |
|---|---|---|---|
| checkout_url | string | – | Stripe Checkout link for card payment |
| current_balance_cents | integer | – | – |
| deposit | object | – | USDC deposit address for crypto payment |
No examples provided.
check_balance ~60
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.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| balance_cents | integer | – | Current credit balance in cents |
| credit_packs | array | – | Available credit packs for purchase |
| recovered_cents | integer | – | Credits recovered from completed payments (if any) |
No examples provided.
get_briefed ~103
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 SPY momentum setups', 'your GLD mean-reversion edge'). Requires at least 5 strong edges in your library. Costs credits.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| news | string | – | Personalized market news digest |
| profile | string | – | Trader profile based on edge library |
| strong_count | integer | – | Number of strong edges in library |
No examples provided.
get_hypothesis ~90
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.
| Name | Type | Req | Description |
|---|---|---|---|
| hypothesis_id | string | yes | The hypothesis ID — from varrd_edges (any depth), search, or scan results. |
| Name | Type | Req | Description |
|---|---|---|---|
| direction | string | – | – |
| formula | string | – | – |
| horizon_results | array | – | – |
| hypothesis_id | string | – | – |
| name | string | – | – |
| win_rate | number | – | – |
No examples provided.
prediction_ai ~233
VARRD's PREDICTION lane: Kalshi / Polymarket / sports markets, through the same engine and the same rules (K-tracking, no lookahead, one hypothesis at a time). PRICE: use is charged for what it cost (the model's usage, no surcharge); nothing has a set price. MULTI-TURN: the first call creates a session; keep passing session_id. Flow: describe the signal in plain language -> 'test it' -> results (per-hold win rate, edge vs the market price, p-values) -> 'trade setup'. Say 'start a new hypothesis' between ideas. Read `state` and `next_steps` every call; `widgets` carry the tables the result is made of.
| Name | Type | Req | Description |
|---|---|---|---|
| league_hint | string | – | Optional league hint for ambiguous team names: NFL, NBA, CFB, MLB, NHL. |
| message | string | yes | Your prediction-market idea, question, or instruction ('test it', 'trade setup'). |
| session_id | string | – | Session id from a previous call. Omit to start a new session. |
| Name | Type | Req | Description |
|---|---|---|---|
| next_steps | array | – | What the user can ask for next |
| session_id | string | – | – |
| state | string | – | Where the flow is: scope, signal built, tested, ... |
| text | string | – | AI response text |
| widgets | array | – | Result tables (event study, retest, trade setup) |
No examples provided.
prediction_edges ~102
FREE, read-only. This account's SAVED prediction edges (Kalshi / Polymarket / sports): the lean rows, or one edge's full saved stats with `edge_id` (verdict, per-hold results, coverage, p-values, every version, the append-only ledger). A pure read of what was validated: nothing re-runs.
| Name | Type | Req | Description |
|---|---|---|---|
| edge_id | string | – | A saved edge id for the full detail. Omit to list. |
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | – |
| edge | object | – | One edge's saved stats (when edge_id is given) |
| edges | array | – | Summary rows (when listing) |
No examples provided.
reset_session ~69
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.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | The session_id to reset. |
| Name | Type | Req | Description |
|---|---|---|---|
| message | string | – | – |
| reset | boolean | – | – |
No examples provided.
search ~96
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.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max results to return. |
| market | string | – | Optional market filter. |
| query | string | yes | Search query — keywords or natural language (e.g. 'momentum strategies', 'RSI oversold'). |
| Name | Type | Req | Description |
|---|---|---|---|
| method | string | – | Search method: embedding or keyword |
| query | string | – | – |
| results | array | – | Matching strategies with win rate, Sharpe, similarity |
No examples provided.
varrd_ai ~575
Talk to VARRD AI. PRICE: use is charged for what it cost (the model's usage, no surcharge); nothing has a set price. Call check_balance for the balance. 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 SPY, QQQ, and IWM') — 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 SPY, QQQ, and IWM' -> 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 TERMIN…
| Name | Type | Req | Description |
|---|---|---|---|
| message | string | yes | Your trading idea, research question, or instruction (e.g. 'test it', 'show trade setup'). |
| session_id | string | – | Session ID from a previous call. Omit to start a new research session. |
| Name | Type | Req | Description |
|---|---|---|---|
| context | object | – | Workflow state, edge verdict, next actions |
| session_id | string | – | Session ID for multi-turn conversation |
| text | string | – | AI response text |
| widgets | array | – | Chart, event study, backtest, or trade setup widgets |
No examples provided.
varrd_edges ~580
YOUR OWN EDGES, LIVE. Free at every depth: they are this account's edges. 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 account has no edges yet, this returns none (it is NOT a general/shared library). To get an edge, test an idea with varrd_ai; it shows here once it is validated and firing, pending or in a trade. THREE LEVELS OF DETAIL (none of them costs anything): depth=0: 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: Direction, occurrence count, EV/trade, stop-loss, take-profit, hold horizon, and current entry prices for ALL active edges in one request. depth=2: 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: setup_code, horizons, analytics, occurrences, and view (interactive chart link for your user, 15 min). Every edge here is Bonferroni-corrected, tested against both zero returns and market baseline, with K-tracking to prevent p-hacking. Out-of-sample validated. Full transparency.
| Name | Type | Req | Description |
|---|---|---|---|
| asset_class | string | – | Filter by asset class: 'futures', 'equities', 'crypto'. |
| depth | integer | – | How much detail: 0 = markets + status, 1 = direction, stats and trade levels for ALL active edges, 2 = full methodology + performance. All free: they are the account's own edges. |
| direction | string | – | Filter by direction: 'LONG' or 'SHORT'. |
| edge_id | string | – | Specific edge ID for depth 1 or 2 detail. Omit to see all edges. |
| market | string | – | Filter by market symbol (e.g. 'SPY', 'BTC'). Omit to see all. |
| section | string | – | Drill into a specific section of a depth=2 edge. Options: setup_code, horizons, analytics, occurrences, view. Omit to get the overview directory. |
| status | string | – | Filter by status: 'firing', 'pending', 'active', or omit for all. |
| timeframe | string | – | Filter by timeframe: '60min', '120min', '240min', '480min', 'daily', 'weekly'. |
No output schema declared.
No examples provided.
How do I install the VARRD — Statistically Validated Trading Edges + AI… MCP server?
VARRD — Statistically Validated Trading Edges + AI… is a hosted endpoint at https://app.varrd.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · app.varrd.com
claude mcp add --transport http augiemazza-varrd 'https://app.varrd.com/mcp'
What is the VARRD — Statistically Validated Trading Edges + AI… MCP server?
VARRD — Statistically Validated Trading Edges + AI… is an MCP server listed in the public MCP registry as io.github.augiemazza/varrd. Validated trading edges across futures, equities, crypto. Live signals, full audit trail. This page covers its hosted endpoint (https://app.varrd.com/mcp).
Is the VARRD — Statistically Validated Trading Edges + AI… MCP server safe to use?
VARRD — Statistically Validated Trading Edges + AI… scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the VARRD — Statistically Validated Trading Edges + AI… MCP server expose?
VARRD — Statistically Validated Trading Edges + AI… exposes 11 tools: varrd_edges, varrd_ai, prediction_ai, prediction_edges, search, and 6 more. Their descriptions and schemas cost roughly 2,497 tokens of context every time the server is loaded.
Does the VARRD — Statistically Validated Trading Edges + AI… MCP server require authentication?
No. We connected to VARRD — Statistically Validated Trading Edges + AI… without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the VARRD — Statistically Validated Trading Edges + AI… MCP server still maintained?
VARRD — Statistically Validated Trading Edges + AI… is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the VARRD — Statistically Validated Trading Edges + AI… MCP server?
VerifyMCP ran 13 checks on VARRD — Statistically Validated Trading Edges + AI…, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.