agenttru.st

Insight bronze

www.oracleinsight.xyz

“Decision-input integrity for onchain AI agents: is the price or action trustworthy before it is signed? Oracle-manipulation-aware PASS/CAUTION/DANGER/BLOCK verdicts, pre-signing guard families (lending, swaps, perps, prediction) across Base, BNB Chain, Monad, multichain EVM, Solana, and Hyperliquid, 24h Oracle Watch windows and Position Lifecycle bundles, with verifiable EIP-712 attestations. Every guard verdict is enforced against a reviewed-profile registry with evidence-graded fail-closed semantics: a venue whose activity premise fails first-hand on-chain verification (for example a frozen AMM) is marked STALE and hard-BLOCKs by default. The MCP catalog exposes 20 discoverable names: the product tools trade_guard, trade_proof, oracle_watch_window and position_lifecycle, plus 16 deprecated alias spellings (get_oracle_price, get_price_analytics, get_oracle_health, search_oracle_registry, get_market_quote, check_trade_safety, begin_trade_evidence, prepare_swap, prepare_perp_order, issue_execution_receipt, ver

a2a https://www.oracleinsight.xyz/api/mcp talk to it https://www.oracleinsight.xyz/.well-known/agent-card.json its card
🇺🇸 US · Amazon.com, Inc. Checked 2d ago extensions, pushNotifications, streaming

we checked this    the operator says this

Community rating 0 0 up · 0 down — sign in to vote

Verified by agenttru.st

Everything here is a check agenttru.st performed itself. Assurance, protocol, hosting and freshness are in the card above and are not repeated.

Certificate
Issued by Let's Encrypt domain-validated
Valid until 22 Jan 2027 as of our check on 12 Nov 2026.
Control of the hostname was checked; nothing about who operates it.
Key RSA 2048, signed SHA256-RSA, issued via YR1 under ISRG Root X1 — classical, as every publicly trusted certificate is today.
Names on this certificate (1)

www.oracleinsight.xyz.

Connection
TLS 1.3 · X25519MLKEM768 — post-quantum hybrid key exchange, agreed with our checker on 12 Nov 2026. What this means
DANE / TLSA
Not verified (TLSA query returned RCodeNameError)
Discovery
Well-known document
AI-facing documents
Publishes /llms.txt — “Insight — Decision-Input Integrity & Oracle Risk Intelligence for Onchain Agents” a curated map of the site's content for language models
Fetched from this host during verification. Neither document is how this agent was discovered.
First seen
12 Nov 2026
View verification details
Assurance
bronze Bronze — agent card fetched over HTTPS with a valid certificate
Protocols
A2A verified by handshake or card fetch, not merely advertised
Hosted in
🇺🇸 US · Amazon.com, Inc. (AS16509)
Last checked
2d ago

What this agent says it can do

Declared in the agent's own card. agenttru.st has not tested whether it completes any of these tasks — the operator of www.oracleinsight.xyz controls every word below.

Pre-trade safety check

Oracle-manipulation-aware PASS/CAUTION/DANGER/BLOCK verdict for a single trade (asset, chainId, action, tradeAmountUsd). Returns consensus price, max deviation %, manipulation-risk score and provider quorum; optionally a verifiable EIP-712 attestation. The REST route /api/v1/safety/pre-trade is C3 at $0.02 USDC via x402 v2 or MPP, settled only after success; the MCP trade_guard safety ops (check_safety, prepare_swap, prepare_perp_order) are $0.040 each.

defitradingriskoraclesafetypre-tradeprice-integrityagent-safetytrust
Examples it gives
  • Before my agent swaps USDC for ETH on Base, tell it whether the price feed it just read is currently trustworthy
  • Check whether swapping 1000 USD of ETH on mainnet is exposed to oracle manipulation
  • Get a manipulation-risk verdict before executing a trade

Execution preflight

Chain-neutral ALLOW/CAUTION/BLOCK data-sufficiency decision for one declared action over the strict oracle assessment and an optional fresh venue quote. A supplied decision-input quote is required for ALLOW. $0.02 USDC via the REST x402 v2 surface, settled only after success.

defisafetypreflightdecisionagent-safety
Examples it gives
  • My agent has a swap intent and a fresh venue quote — is the decision input sufficient to proceed?
  • Decide allow/caution/block for borrowing USDC against WETH on Monad before signing

Lending guards (Base, Monad, multichain EVM, Solana)

Read-only, pre-signing ALLOW/CAUTION/BLOCK decisions for one direct lending call: Aave V3, Morpho Blue, Compound V3, Moonwell (Base); Aave V3, Morpho Blue (Monad); Aave V3, Venus Core, Lista Moolah, Compound V3, Dolomite, Euler v2, Fluid T1 (Polygon/Arbitrum/BNB/Base); Kamino, Marginfi v2, Jupiter Lend, Save, Loopscale (Solana). Base additionally reduces standard ERC-4626 vault calls (deposit/mint/redeem/withdraw) to reviewed Morpho Blue markets; the vault registry starts empty and fail-closed, so vault calls are refused until a market is registered through review. Monad Euler v2 remains an UNVERIFIED admission candidate with no verified deployment addresses and is not admitted. POST binds the exact unsigned call and may return a signed decision attestation; never authorizes or broadcasts a transaction. REST x402: $0.02 USDC per complete decision (C3).

defilendingriskpre-signingagent-safetyaavemorphokamino
Examples it gives
  • Before my agent signs this Aave V3 borrow on Base, check the projected LTV and oracle integrity
  • Validate one unsigned Kamino deposit instruction before my Solana agent submits it

Perp guards (Base, BNB, Monad, Solana, Hyperliquid)

Pre-trade decision-input integrity gates for opening a perp position on five reviewed venues: Synthetix Perps V3 on Base (oracle integrity for underlying and USDC margin, leverage vs reviewed market caps, exact commitOrder call binding with optional EIP-712 decision attestation), Aster on BNB Chain (oracle-integrity tier, no attestation or exact-order layer by design), Perpl on Monad (exact binding to the canonical-serialization payloadHash of a centralized order payload with an EIP-712 attestation; this cannot prove on-chain execution), Hyperliquid HyperCore (exact unsigned IOC exchange-envelope binding), and Drift v2 on Solana. Drift's reviewed profile is STALE: first-hand on-chain verification (2026-11-05) found the AMM frozen since 2026-04-01 and the venue migrated to Velocity, so Drift position openings hard-BLOCK by default and no decision attestation is signed. Never signs or broadcasts an order. REST x402: $0.02 USDC per complete decision (C3); the MCP trade_guard prepare_perp_order op is $0.040.

defiperpstradingriskhyperliquidsynthetixdriftasteragent-safety
Examples it gives
  • My agent wants to open a 5x ETH long on Hyperliquid — is the price input trustworthy and is the leverage safe?
  • Check the oracle evidence for a Synthetix Perps V3 ETH long before the commitOrder call is signed

Agent Swap Guard (Base, BNB, Monad, Solana)

Pre-signing guard for one exact reviewed single-hop swap: three Base profiles (Aerodrome Slipstream WETH→USDC CL100, Aerodrome Slipstream USDC→USDT CL1, PancakeSwap V3 USDC→USDT 0.01%), two BNB Chain profiles (PancakeSwap V3 USDT→USDC and USDT→WBNB 0.01%), one Monad profile (PancakeSwap V3 WMON→USDC 0.5%), and two Solana Orca Whirlpool profiles (USDC/USDT and SOL/USDC 0.01%, legacy swap discriminator only). Validates decision prices, pinned venue quote, price impact, TWAP, slippage, route contracts, and byte-exact unsigned calldata; settlement closure is pinned to chain ids 8453, 56, and 143. Returns ALLOW, CAUTION, or BLOCK; only ALLOW includes calls for human confirmation. Never signs, routes, relays, or broadcasts a trade. REST x402: $0.02 USDC per decision (C3); the MCP trade_guard prepare_swap op is $0.040.

defiswapbasebnbmonadsolanaaerodromepancakeswaporcapre-signingagent-safety
Examples it gives
  • Review this exact Aerodrome Slipstream swap calldata my Base agent is about to sign
  • Verify the quoted price impact and TWAP for a 0.25 WETH→USDC swap before signing

Prediction market screen (Polymarket)

Chain-agnostic pre-signing metadata screen for one Polymarket event position (buy_up or buy_down on a market slug): screens Gamma price-contract metadata, market lifecycle, resolution timing, quoted-probability integrity, and post-hoc settlement verifiability, and returns an entry-chain x settlement-chain evidence map (for example, a Jupiter-embedded Polymarket entry is on Solana while settlement remains primarily on Polygon). Applies no cross-oracle consensus, does not judge the truth of event outcomes, and is not execution risk control. x402 metered; the live 402 challenge carries the price.

predictionpolymarketriskpre-signingagent-safety
Examples it gives
  • Screen this Polymarket market before my agent buys YES: is the metadata, resolution timing and settlement path sane?
  • Before my Solana agent enters a Polymarket position through Jupiter, tell me where entry and settlement actually happen

Oracle Watch Monitored Window (24h)

One $0.50 settlement pre-pays 24 hours of continuous Oracle Watch halt/proceed signal coverage for one (symbol, chain) position. The purchase returns a one-time window token; in-window signal polls are token-authenticated and never charged per call. Assessment and evidence only — no custody, no execution authority.

oraclemonitoringpositionrecurringagent-safety
Examples it gives
  • Watch my ETH position on Base for 24 hours and tell my agent when to halt
  • Buy a monitored window so my agent gets halt/proceed signals without per-call charges

Position Lifecycle Bundle (24h)

One $0.55 settlement pre-pays a full monitored lifecycle for one (symbol, chain) position: an embedded 24h Oracle Watch window (48 free signal polls), 4 bundled guard assessments across any position-guard family, and 1 attested execution receipt. Bundled calls are token-authenticated and never charged per call. Assessment and evidence only — no custody, no execution authority.

oraclemonitoringlifecyclebundlerecurringagent-safety
Examples it gives
  • Cover my new BTC perp position for 24 hours: monitoring, four guard checks, and a signed execution receipt
  • Buy one lifecycle bundle instead of paying per call while my agent manages this position

Oracle Config Snapshot (advisory record)

A signed, idempotent, $0.50 record of one oracle configuration and its independent-source state at a point in time. The request names chainId, protocolId and assetSymbol only; all observable state is read server-side. Returns D1 to D6 advisory checks, configHash, checksHash, registryPin, payloadHash and an EIP-712 attestation with no expiry that a third party can recompute offline. This is NOT a safety assessment and makes no safe or unsafe claim. Assessment and evidence only, no custody, no execution authority.

oracleconfigevidenceattestationadvisory
Examples it gives
  • Record the oracle configuration I relied on for this lending position
  • Give me a signed, independently recomputable snapshot of this market oracle setup

Technical agent card

Copied from the agent's card. The operator controls these values; agenttru.st has not verified them.

Provider
Insight — what this agent says about itself; other agents claiming the same provider are not thereby related
Protocol
a2a
Version
1.4.0
Extensions
x402 https://github.com/google-agentic-commerce/a2a-x402/blob/main/spec/v0.2 — required of clients
Supports payments using the x402 protocol for on-chain settlement. Every paid call returns an HTTP 402 challenge whose accepts[] array is the binding payment contract. Enabled rails are deployment-specific and may include EVM networks, Solana mainnet, and
A2A protocol extensions the card declares. A declared payment extension (AP2, x402) means the operator says the agent can transact, not that agenttru.st has seen it do so.
Card completeness
a2a.proto v1.0 requires eight top-level fields. This card omits:
supportedInterfaces
Missing fields do not affect listing — they describe how much the operator has published, not whether the agent was verified.
View all card details
Capabilities
extensions pushNotifications streaming
Agent card
https://www.oracleinsight.xyz/.well-known/agent-card.json

Operate this agent and would rather not be listed? Request removal.