01
Insight evaluates evidence
Cross-source agreement, deviation, freshness, peg signals, and reason codes are returned as an assessment—not a promise that a price is correct.
Loading page
Decision-input integrity · Oracle evidence before action
Insight turns source-level oracle context into an explainable assessment before a person, application, or agent acts. Monitor the same conditions between actions and keep evidence that can be checked independently when issuance is enabled.
01 — Responsibility boundary
This page is an assessment surface, not an authorization or transaction-execution surface. It makes the oracle inputs legible so your own policy can make the next decision.
Cross-source agreement, deviation, freshness, peg signals, and reason codes are returned as an assessment—not a promise that a price is correct.
Your person, agent, or application decides whether to proceed, request review, reduce exposure, or halt. Insight never controls your signer.
Where attestation issuance is configured, the returned assessment can include an independently verifiable record of the evaluation.
02 — Assess before submitting
Describe the asset, chain, action, and size. Insight evaluates observable oracle conditions and returns a machine-readable verdict with the factors behind it. Your policy decides how to respond.
Sign in or provide an API key below to run a live check.
Fill in the trade intent and run a check. Insight will aggregate cross-oracle consensus, deviation, freshness and depeg signals into a single safety verdict.
The same assessment is available through the REST API, MCP tool, and Guard SDK.
03 — Watch between actions
A pre-trade assessment captures one moment. Oracle Watch exposes changed conditions for long-running workflows so an operator or policy can choose to pause, continue, or investigate.
Sign in or provide an API key below to run a live check.
Pick an asset and run Oracle Watch. Insight aggregates live cross-oracle deviation, agreement, quorum, outliers and staleness into one verdict an agent can gate on.
Call the MCP tool:
tool: oracle_watch
{
"symbol": "ETH",
"chain": "ethereum"
}
The agent returns a machine-readable verdict:
- Verdict: NORMAL | CAUTION | DANGER
- Recommendation: proceed | proceed_with_caution | halt
- Reason: within_tolerance | deviation_agreement_outlier_or_stale | deviation_or_agreement_breached_danger | insufficient_cross_oracle_quorum | ml_forward_risk_high | no_cross_oracle_coverage
Also gate on the composite Credibility Trust Score (0-100, low|medium|high).Use REST from your stack, MCP for an agent runtime, or Guard SDK for a bounded integration path. Each option leaves policy, signing, and submission under your control.