# Collar Guardrail — Pre-Trade Risk Layer

- Registry name: `io.github.aiguardrail/backend` · version 1.0.5
- Categories (automatic, keyword rules): Markets & trading, Finance & markets, Payments & accounting
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): experimental, extensions, logging, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.aiguardrail%2Fbackend
- Server page: https://mcpstation.net/s/io.github.aiguardrail--backend.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

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

## Tools (as reported by the server, not verified)

- `evaluate\_trade`: Pre-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, use \`evaluate\_trade\_paid\` \(Tier 2, $25,000\) which settles an x402 payment on-chain.
- `evaluate\_trade\_paid`: Pre-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. FLOW ---- 1. Call WITHOUT payment\_proof → the tool returns a \`PaymentRequiredOutput\` describing the
- `check\_token\_safety`: Honeypot / 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=danger, the next \`evaluate\_trade\` for the same contract is automatically denied regardless of any oth
- `simulate\_balance`: Simulate a wallet's ERC-20 balance after a hypothetical trade using eth\_call state override. Read-only: no transaction is ever sent.
- `get\_supported\_assets`: List every asset in the guardrail's official Robinhood Chain registry, with its canonical contract address.
- `verify\_audit\_trail`: Verify the tamper-evident audit trail for a wallet's past guardrail decisions.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html