Skip to main content
Glama

Server Details

Verifiable, deterministic risk math for autonomous agents; re-runnable proof on every answer.

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL

Glama MCP Gateway

Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.

MCP client
Glama
MCP server

Full call logging

Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.

Tool access control

Enable or disable individual tools per connector, so you decide what your agents can and cannot do.

Managed credentials

Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.

Usage analytics

See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.

100% free. Your data is private.

Tool Definition Quality

Score is being calculated. Check back soon.

Available Tools

9 tools
event_volEvent Implied-Move
Read-onlyIdempotent
Inspect

Options-implied expected move around a scheduled event (FOMC/CPI/earnings/etc.). Given spot, ATM implied vol, and days-to-event, returns the 1σ move, the straddle-implied expected ABSOLUTE move (risk-neutral E|ΔS|), and the probability of exceeding move thresholds. Given the vol term structure across the event (ATM IV of the expiry before vs after), it ISOLATES the event's own priced-in move (the Wright event-day technique). Self-checked: the straddle equals a numerical integral of |S_T−S₀|. This is the magnitude that macro calendars (which give only date + impact label) leave out.

ParametersJSON Schema
NameRequiredDescriptionDefault
TNoyears (or daysToEvent)
spotYescurrent spot price
atmIvNoATM IV as a decimal (alternative to atmIvPct)
atmIvPctNoATM IV in % (or atmIv decimal)
daysAfterNodays to the after-event expiry
daysBeforeNodays to the before-event expiry
ivAfterPctNoATM IV (%) of the expiry just AFTER the event
daysToEventNodays until the event
ivBeforePctNoATM IV (%) of the expiry just BEFORE the event
thresholdsPctNomove thresholds (%) for probability-of-exceeding

Output Schema

ParametersJSON Schema
NameRequiredDescription
okNofalse when the engine rejected the input
spotNospot the computation is anchored on
proofNoVerifiability envelope: echoed inputs, engine codeHash, contentHash of this exact result, self-checks, EIP-712 signature (EAS-ready). Re-run the open engine on `inputs` to reproduce the result byte-for-byte.
checksNoGround-truth self-checks; the result is untrustworthy if any fails.
methodNotechnique + assumptions used
atmIvPctNoATM IV used (%)
horizonDaysNohorizon in days
expectedMoveNo1σ move + straddle-implied expected |ΔS| (risk-neutral)
eventIsolationNothe event's own priced-in move, isolated from the term structure (when before/after IVs are given)
probabilityMoveBeyondNoprobability of exceeding each move threshold
exec_verifyExecution-Quality Verifier
Read-onlyIdempotent
Inspect

Deterministic execution-quality / fair-fill verification. Given a completed swap (amountIn, amountOutRealized) plus either the pre-trade pool reserves+fee (constant-product) or a fair reference price, returns how many basis points the fill lost to ADVERSE execution (sandwich/MEV/stale) beyond the unavoidable fee + own price impact. Proves that a fill "within slippage tolerance" can still have been robbed. Call after a swap to detect being sandwiched.

ParametersJSON Schema
NameRequiredDescriptionDefault
feeTierNopool fee as fraction, e.g. 0.003
amountInYesinput amount actually sent
fairPriceNoreference mode: fair out-per-in price at submit time
reserveInNopool reserve of input token, pre-trade (constant-product mode)
reserveOutNopool reserve of output token, pre-trade
amountOutRealizedYesoutput amount actually received
slippageTolerancePctNothe slippage setting used, to demonstrate within-tolerance-yet-robbed

Output Schema

ParametersJSON Schema
NameRequiredDescription
okNofalse when the engine rejected the input
modeNoconstant-product or reference-price mode
noteNointerpretation guidance
proofNoVerifiability envelope: echoed inputs, engine codeHash, contentHash of this exact result, self-checks, EIP-712 signature (EAS-ready). Re-run the open engine on `inputs` to reproduce the result byte-for-byte.
checksNoGround-truth self-checks; the result is untrustworthy if any fails.
verdictNoplain-language verdict
midPriceNopre-trade mid price
honestOutNooutput an honest execution would have delivered
adverseValueOutNovalue lost to adverse execution, in output-token units
honestFillPriceNothe fill price an honest execution would have produced
realizedFillPriceNothe fill price actually received
unavoidableCostBpsNofee + own price impact — the honest, unavoidable cost (bps)
adverseExecutionBpsNobps lost to ADVERSE execution beyond the honest cost
lp_riskLP Divergence-Loss Gate
Read-onlyIdempotent
Inspect

Forward-looking liquidity-provision risk. Given a realized price ratio (for impermanent loss) and/or a volatility + horizon (for expected divergence / LVR), returns the closed-form IL, the expected −σ²T/8 divergence, and — with a fee APR — the net forecast and breakeven volatility (the vol above which fees no longer cover the bleed). Self-checked: the IL closed form is verified at the token level against explicit constant-product amounts. Call before providing liquidity to see whether the fee yield can plausibly beat the divergence loss.

ParametersJSON Schema
NameRequiredDescriptionDefault
feeAprPctNoannualized fee yield estimate
capitalUsdNoposition capital in USD — losses are also reported in USD
priceRatioNorealized P1/P0 for realized IL
volatilityNoper-period vol (decimal) for expected divergence
horizonPeriodsNoperiods (default 1)
periodsPerYearNodefault 365
concentrationFactorNoV3 amplifier ≥1 (default 1)

Output Schema

ParametersJSON Schema
NameRequiredDescription
okNofalse when the engine rejected the input
modelNomodel assumptions used
proofNoVerifiability envelope: echoed inputs, engine codeHash, contentHash of this exact result, self-checks, EIP-712 signature (EAS-ready). Re-run the open engine on `inputs` to reproduce the result byte-for-byte.
checksNoGround-truth self-checks; the result is untrustworthy if any fails.
realizedILNoclosed-form impermanent loss at the realized price ratio
feeVsDivergenceNonet forecast and breakeven volatility vs the fee APR
expectedDivergenceNoexpected divergence loss / LVR over the horizon (−σ²T/8 law)
concentrationFactorNoV3 concentration amplifier applied
options_riskOptions Book Risk (Greeks + SPAN)
Read-onlyIdempotent
Inspect

Portfolio greeks (delta/gamma/vega/theta/vanna/volga) + SPAN-style scenario margin for an options book on Black-76. Given a list of legs {type, strike, expiryDays, iv, quantity(signed)} and a forward, returns aggregate greeks, first-order P&L per underlying move, and the worst-case loss over a price×vol grid. Self-checked: analytic greeks are verified against finite-difference derivatives of the repriced book. Call to size an options book's true net risk and margin — not the sum of per-leg notionals.

ParametersJSON Schema
NameRequiredDescriptionDefault
rNodiscount rate, default 0
forwardNoshared forward price (or set per position)
positionsYesoption legs of the book
scanRangePctNoSPAN price scan range, default 0.15
volShiftVolPtsNoSPAN vol shift in vol-points, default 10

Output Schema

ParametersJSON Schema
NameRequiredDescription
okNofalse when the engine rejected the input
modelNoBlack-76 assumptions used
proofNoVerifiability envelope: echoed inputs, engine codeHash, contentHash of this exact result, self-checks, EIP-712 signature (EAS-ready). Re-run the open engine on `inputs` to reproduce the result byte-for-byte.
checksNoGround-truth self-checks; the result is untrustworthy if any fails.
greeksNoaggregate delta/gamma/vega/theta/vanna/volga — each verified vs finite differences
positionsNoper-leg pricing breakdown
spanMarginNoworst-case loss over the price×vol scenario grid (SPAN-style margin)
portfolioValueNomark-to-model value of the book
positionsCountNonumber of legs priced
pnlPerUnderlyingPctMoveNofirst-order P&L per % move of the underlying
perp_gatePerp Liquidation Gate
Read-onlyIdempotent
Inspect

Deterministic perpetual-futures risk. Given a position (entry, size, margin/leverage, maint-margin/maxLeverage), returns the exact liquidation price, the % adverse move to liquidation, effective leverage, and (if a funding rate is given) the funding drag. Pass a Hyperliquid symbol (e.g. BTC) to auto-fill live mark price, funding, and max leverage. Includes a self-check proving the liquidation invariant. Call this BEFORE opening or sizing any leveraged perp position — an agent that knows its true liquidation distance does not get surprise-liquidated.

ParametersJSON Schema
NameRequiredDescriptionDefault
sideNodefault long
sizeNoposition size in base units (or pass notional)
venueNolive-data venue (default hyperliquid)
marginNoisolated margin posted (or pass leverage)
symbolNoperp symbol (e.g. BTC) — auto-fills live markPrice, fundingRateHourly, and the margin source (Hyperliquid notional tiers or dYdX maintenance rate); also defaults entryPrice to the live mark
leverageNoposition leverage (alternative to margin)
notionalNoposition notional in quote/USD
markPriceNocurrent mark; distance-to-liq measured from here
entryPriceNodefaults to live mark if a symbol is given
maxLeverageNovenue max leverage for the asset
horizonHoursNohorizon for the funding-drag estimate, in hours
maintMarginRateNoe.g. 0.0125; or pass maxLeverage (mmr = 0.5/maxLeverage)
fundingRateHourlyNohourly funding rate (Hyperliquid funds hourly)

Output Schema

ParametersJSON Schema
NameRequiredDescription
okNofalse when the engine rejected the input
modelNomodel assumptions used
proofNoVerifiability envelope: echoed inputs, engine codeHash, contentHash of this exact result, self-checks, EIP-712 signature (EAS-ready). Re-run the open engine on `inputs` to reproduce the result byte-for-byte.
checksNoGround-truth self-checks; the result is untrustworthy if any fails.
fundingNofunding drag over the horizon (when a funding rate is given)
marginTierNovenue margin tier the notional falls into
liquidationPriceNoexact price at which the position liquidates
effectiveLeverageNonotional / margin actually run
initialMarginRatePctNoinitial margin rate applied (%)
moveToLiquidationPctNoadverse % move (from mark) that triggers liquidation
maintenanceMarginRatePctNomaintenance margin rate applied (%)
portfolio_gateCross-Venue Portfolio Gate
Read-onlyIdempotent
Inspect

Cross-venue portfolio risk. Given positions across venues [{venue, asset|symbol, side, size, entryPrice, margin|leverage, maxLeverage|marginTiers}] — OR just account: a Hyperliquid 0x address, whose FULL live book (positions, margins, account equity, the venue's own liquidation prices) is pulled keylessly — returns TRUE net exposure per underlying, the leg that liquidates FIRST (the binding constraint), concentration (HHI / effective independent bets), and a correlated-crash stress counting how many legs liquidate SIMULTANEOUSLY when the market moves ±X% (correlation→1, the Oct-10-2025 crash regime). Pass Hyperliquid symbols to auto-fill live mark/leverage/margin-tiers. Self-checked (exposure reconciliation, per-leg liquidation invariant, nearest=min, monotone stress, venue-liquidation cross-check). Call to see whether independently-sized bets are secretly ONE bet that blows up together.

ParametersJSON Schema
NameRequiredDescriptionDefault
accountNoOR: a Hyperliquid account address (0x…) — the full live book (positions, margins, equity, venue liquidation prices) is pulled keylessly; explicit positions take precedence.
betaTierNobeta regime for the factor stress: mild | moderate | severe — cross-event validated tiers (pre-registered). Default = worst-case single-event table; explicit betas override.
positionsNolegs: {venue, asset|symbol, side long|short, size, entryPrice, markPrice?, margin|leverage, maxLeverage|maintMarginRate|marginTiers}. A Hyperliquid symbol auto-fills live mark/leverage/tiers.
shockScenariosPctNocorrelated market moves (%) to stress; default [5,10,20,30]

Output Schema

ParametersJSON Schema
NameRequiredDescription
okNofalse when the engine rejected the input
modelNomodel assumptions used
proofNoVerifiability envelope: echoed inputs, engine codeHash, contentHash of this exact result, self-checks, EIP-712 signature (EAS-ready). Re-run the open engine on `inputs` to reproduce the result byte-for-byte.
checksNoGround-truth self-checks; the result is untrustworthy if any fails.
positionsNoper-leg breakdown with each liquidation price
concentrationNoHHI + effective number of independent bets
positionsCountNonumber of legs analyzed
totalNetNotionalNonet notional after long/short netting
nearestLiquidationNothe leg that liquidates FIRST — the binding constraint
netExposureByAssetNoTRUE net exposure per underlying (longs netted against shorts)
totalGrossNotionalNosum of |notional| across legs
correlatedShockStressNoper-scenario: how many legs liquidate simultaneously at a correlated ±X% move
risk_attestMerkle Batch Attestation
Read-onlyIdempotent
Inspect

Batch the content-hashes from many Quiver proof envelopes into ONE Merkle root plus per-item inclusion proofs, so a single on-chain anchor (your wallet's tx) attests all of them at once. Self-checked for completeness (every item verifies) and soundness (a non-member does not). Use to make a batch of risk computations cheaply and permanently attestable for audit/liability, without a chain write per computation.

ParametersJSON Schema
NameRequiredDescriptionDefault
itemsNoproof envelopes (uses proof.contentHash) or raw content-hashes (hex)
contentHashesNoalternatively, raw content-hashes

Output Schema

ParametersJSON Schema
NameRequiredDescription
okNofalse when the engine rejected the input
proofNoVerifiability envelope: echoed inputs, engine codeHash, contentHash of this exact result, self-checks, EIP-712 signature (EAS-ready). Re-run the open engine on `inputs` to reproduce the result byte-for-byte.
anchorNoEIP-712 (EAS-ready) attestation payload for the single on-chain anchor
checksNoGround-truth self-checks; the result is untrustworthy if any fails.
verifyNohow to verify inclusion against the root
algorithmNohash/tree construction used
leafCountNonumber of items batched
merkleRootNothe single root that attests every item
attestationsNoper-item inclusion proofs
duplicateLeavesNoduplicate content-hashes detected in the batch
size_gateKelly Size Gate
Read-onlyIdempotent
Inspect

Deterministic position sizing (fractional Kelly) + risk-of-ruin. Given an edge — discrete {winProb, winLossRatio} or continuous {expectedReturn, volatility} — and a bankroll, returns the fractional-Kelly size and the probability of ever drawing down to 50/75/90%. The direct antidote to over-betting: full Kelly rides thin edges to ruin; this defaults to quarter-Kelly. Call before sizing ANY position.

ParametersJSON Schema
NameRequiredDescriptionDefault
winProbNodiscrete mode: win probability in (0,1)
bankrollNobankroll in account units — recommended sizes are returned in the same units
volatilityNocontinuous mode: volatility per period (sigma)
winLossRatioNodiscrete mode: net win/loss odds b
kellyFractionNofraction of full Kelly to bet (default 0.25)
expectedReturnNocontinuous mode: excess return per period (mu)

Output Schema

ParametersJSON Schema
NameRequiredDescription
okNofalse when the engine rejected the input
modeNodiscrete or continuous
noteNoplain-language guidance
modelNomodel assumptions used
proofNoVerifiability envelope: echoed inputs, engine codeHash, contentHash of this exact result, self-checks, EIP-712 signature (EAS-ready). Re-run the open engine on `inputs` to reproduce the result byte-for-byte.
checksNoGround-truth self-checks; the result is untrustworthy if any fails.
hasEdgeNofalse when the edge is non-positive (bet nothing)
leverageNoimplied leverage of the recommended size
riskOfRuinNoprobability of ever drawing down to 50/75/90% of bankroll
recommendedSizeNorecommended bet size in bankroll units
expectedLogGrowthNoexpected log-growth rate at the recommended size
fullKellyFractionNofull-Kelly fraction of bankroll (the ruinous ceiling, not the recommendation)
kellyFractionUsedNofraction of full Kelly applied (default 0.25)
impliedPortfolioVolPctNoportfolio volatility implied by the recommended size (%)
recommendedBetFractionNorecommended bet as a fraction of bankroll
treasury_riskTreasury Depeg & Concentration
Read-onlyIdempotent
Inspect

Stablecoin / on-chain treasury risk. Given a book of positions [{asset, amountUsd, apyPct, venue, chain, pegTarget, depegProbAnnual}], returns concentration (Herfindahl by asset/venue/chain + breaches over a limit), depeg stress (explicit scenarios + a worst-single-depeg scan), weighted and risk-adjusted yield. Self-checked: HHI == Σw², weights sum to 1, depeg-loss identity. Call to size a treasury's real risk — issuer/venue/chain concentration and depeg exposure — not just its headline APY.

ParametersJSON Schema
NameRequiredDescriptionDefault
positionsYestreasury holdings
depegFloorNoworst-single-depeg stress floor (default 0.90)
depegScenariosNo[{asset, price}] explicit depeg stresses
concentrationLimitPctNoflag any single exposure above this (default 25)

Output Schema

ParametersJSON Schema
NameRequiredDescription
okNofalse when the engine rejected the input
modelNomodel assumptions used
proofNoVerifiability envelope: echoed inputs, engine codeHash, contentHash of this exact result, self-checks, EIP-712 signature (EAS-ready). Re-run the open engine on `inputs` to reproduce the result byte-for-byte.
checksNoGround-truth self-checks; the result is untrustworthy if any fails.
verdictNoplain-language verdict
totalUsdNototal treasury size in USD
depegStressNoexplicit depeg scenarios + worst-single-depeg scan
concentrationNoHerfindahl (HHI) by asset/venue/chain + limit breaches
weightedApyPctNoholdings-weighted headline APY (%)
riskAdjustedApyPctNoyield after expected depeg loss (%)
expectedAnnualDepegLossUsdNoexpected annual loss from depeg probabilities (USD)

Discussions

No comments yet. Be the first to start the discussion!

Try in Browser

Your Connectors

Sign in to create a connector for this server.

Resources