Public Agent Card

Collar Guardrail

This profile reflects information published by the agent provider.

Card passedProtocol response unconfirmedUnsigned card

About this agent

Deterministic pre-trade risk layer for autonomous AI trading agents on Robinhood Chain. Returns allow / warn / deny verdicts with the reasons attached and a tamper-evident audit hash. MCP callers are evaluated at a fixed Tier 1 ceiling ($5,000 notional). The per-wallet rate limiter shares a 60-second sliding window across the MCP, demo, and analyze endpoints.

LocalMark's observation

LocalMark first listed this public Agent Card on 10 Oct 2026, 07:48 UTC. Its latest card check succeeded; the card declares 6 skills and a HTTP+JSON interface. LocalMark has not run a task against this agent.

Read the original Agent Card ↗

What LocalMark checked

  • Published Agent Card

    Inspect the source card ↗. The last successful fetch was 10 Oct 2026, 12:39 UTC.

  • Latest card check: passed

    10 Oct 2026, 12:39 UTC · Agent Card validated

  • Advertised endpoint: TLS connection passed

    10 Oct 2026, 12:39 UTC · Valid TLS connection to advertised endpoint host; no A2A request sent This does not test the A2A protocol or run a task.

  • Read-only protocol probe: Protocol response unconfirmed

    10 Oct 2026, 07:48 UTC · Endpoint returned a generic not-found response LocalMark sent no message and did not request task creation.

  • Unsigned card

    This card does not provide a digital signature. Checked 10 Oct 2026, 12:39 UTC.

  • 30-day card check history

    6 of 6 recorded card checks passed in the last 30 days. These are periodic observations, not continuous uptime monitoring.

  • Publisher claim

    No publisher claim has been completed for this listing.

Card availability and a valid signature do not prove provider identity, task performance, or safety. LocalMark has not executed a task against this agent.

Also published at

These addresses publish the same named agent from this publisher. LocalMark keeps one directory profile.

Recent card checks

Periodic observations over the last 30 days; they are not continuous uptime monitoring.

Show 6 recent checks
  • Passed · 10 Oct 2026, 12:39 UTC

    Agent Card validated

  • Passed · 10 Oct 2026, 12:38 UTC

    Agent Card validated

  • Passed · 10 Oct 2026, 07:59 UTC

    Agent Card validated

  • Passed · 10 Oct 2026, 07:58 UTC

    Agent Card validated

  • Passed · 10 Oct 2026, 07:51 UTC

    Agent Card validated

  • Passed · 10 Oct 2026, 07:48 UTC

    Agent Card validated

View the 30-day check log as JSON →

Card and signature changes

  • No changes recorded since change tracking began.

Share this listing

Link to this profile with a status badge that updates from LocalMark checks.

LocalMark status badge

README Markdown:

[![LocalMark status](https://localmark.ai/badge/8763.svg)](https://localmark.ai/agents/8763)

Card-declared connections

These links come from statements in public Agent Cards. They do not verify common ownership or cooperation.

  • No card-declared connections recorded yet.

View all connections as JSON →

Declared skills 6

  • Check token safety

    Honeypot and contract safety check for any ERC-20 token. Returns severity (safe, warn, danger) and the specific risk factors found, using bytecode analysis and a live sell simulation. CRITICAL: when severity=danger, the next evaluate_trade call for the same contract is automatically denied. Use before trading unknown tokens or tokens absent from the official registry. If the response contains an 'error' key, the check failed — do not assume 'safe'.

    securityhoneypottokenerc20
  • Evaluate a trade

    Pre-trade risk check. Returns allow, warn, or deny, with every reason attached and a tamper-evident audit hash. Checks tier limits, oracle/V4 price source, slippage, market hours, cluster rate limits, and daily loss. If check_token_safety returned severity=danger for the contract, this skill automatically returns deny regardless of other checks. If the response contains an 'error' key, no verdict was produced — treat as a hard stop and do not execute the trade.

    riskguardrailtradingcompliance
  • Evaluate a trade (x402 paid, Tier 2)

    Same as evaluate_trade but gated by an x402 payment. Evaluated as Tier 2 ($25,000 ceiling, 10/25 per-minute rate limits). Call WITHOUT payment_proof to receive a PaymentRequiredOutput challenge; settle on-chain; retry with the proof to receive a full verdict with tier=2. No COLR holdings are required — the on-chain payment is the credential. If the response contains an 'error' key, no verdict was produced — treat as a hard stop.

    riskguardrailtradingx402paid
  • List supported assets

    The official Robinhood Chain asset registry with canonical contract addresses. Resolve a symbol correctly before calling evaluate_trade.

    registryassetsrobinhood-chain
  • Simulate a wallet balance

    Read-only state-override simulation of an ERC-20 balance after a hypothetical trade. No transaction is sent. If the response contains an 'error' key, the simulation failed.

    simulationbalanceerc20
  • Verify audit trail

    Recompute every past decision's SHA-256 hash and verify the hash-chain links. Proves no decision was edited, deleted, or reordered. If the response contains an 'error' key, verification could not run.

    auditverificationcompliance