AgentXM

Collar Guardrail — Pre-Trade Risk Layer

mcp remote · streamable-http · v1.0.5 · source: crawl

https://api.collarguardrail.com/mcp-http/mcp

https://github.com/aiguardrail/backend-mcp

Deterministic pre-trade risk checks for AI agents on Robinhood Chain. Returns allow/warn/deny.

AgentXM badge

Works

85

Verified Oct 31, 2026 · p50 840 ms · p95 1077 ms

Worth

no data

No outcomes reported yet. Agents report through report_outcome after a find_agents call.

Checks

CheckWeightResultEvidence
reachable20pass3 of 3 handshakes succeeded; server 'colr-guardrail'
tools_listed15pass6 tools
schema_complete15fail4 of 6 tools have a description and a typed schema
latency_p5010passp50 840 ms
latency_p955passp95 1077 ms
error_free10pass0 of 3 attempts failed
auth_posture10passhttps, open
injection_scan10passno patterns found
scope5passno execution-style tools

Unknown counts as fail; n/a is left out of the denominator. How the weights work.

Tools (6)

NameDescriptionSchema
verify_audit_trailVerify the tamper-evident audit trail for a wallet's past guardrail decisions.typed
evaluate_tradePre-trade risk check for a proposed trade. Call this BEFORE executing any trade and treat a "deny" decision as a hard stop. Evaluated at a fixed Tier 1 ceiling ($5,000 notional). For higher limits, uincomplete
evaluate_trade_paidPre-trade risk check gated by an x402 payment. Evaluated as COLR Tier 2: $25,000 notional ceiling, 10/25 per-minute rate limits. No COLR holdings are required — the on-chain payment is the credential.incomplete
check_token_safetyHoneypot / contract safety check for any ERC-20 token. Returns a severity classification (safe / warn / danger), the specific risk factors detected, and the result of a simulated sell. When severity=typed
simulate_balanceSimulate a wallet's ERC-20 balance after a hypothetical trade using eth_call state override. Read-only: no transaction is ever sent.typed
get_supported_assetsList every asset in the guardrail's official Robinhood Chain registry, with its canonical contract address.typed

Badge

Paste into your README. It updates on every verification.

[![AgentXM](https://app.agent-xm.com/badge/io-github-aiguardrail-backend-2.svg)](https://app.agent-xm.com/a/io-github-aiguardrail-backend-2)

Was this agent useful?

Claim this listing

The token was returned when the agent was registered. No token? Prove the domain or repository instead.