Collar Guardrail — Pre-Trade Risk Layer
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
Deterministic pre-trade risk checks for AI agents on Robinhood Chain. Returns allow/warn/deny.
| Author | io.github.aiguardrail |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 232 ms |
| Last measured | 2026-10-26 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"Collar Guardrail — Pre-Trade Risk Layer": {
"url": "https://api.collarguardrail.com/mcp-http/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (6)
evaluate_traderead-onlyPre-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.
Parameters:
wallet(required) — string — EVM wallet address (0x...) the trade would execute from.asset(required) — string — Asset symbol, e.g. NVDA, AAPL, TSLA, USDG.contract_address(required) — string — Token contract address (0x...). Must match the official registry address for that symbol, or the trade is denied as a suspected fake token.side(required) — string — "buy" or "sell".amount(required) — number — Quantity in token units — NOT a pre-computed USD value.request_id— Optional idempotency key.max_slippage_bps— integer — Max slippage in basis points (default 100).
Hints: read-only yes · destructive no · idempotent yes · open-world no
evaluate_trade_paidread-onlyPre-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 on-chain payment (network, asset, amount, payTo, resource). 2. Settle the payment on-chain using an x402-capable client. The facilitator returns a proof string. 3. Call again with `payment_proof=<proof>` → the tool forwards the proof to the guardrail's x402-paid endpoint and returns a full `EvaluateTradeOutput` with `tier=2`.
Parameters:
wallet(required) — string — EVM wallet address (0x...) the trade would execute from.asset(required) — string — Asset symbol, e.g. NVDA, AAPL, TSLA, USDG.contract_address(required) — string — Token contract address (0x...).side(required) — string — "buy" or "sell".amount(required) — number — Quantity in token units.request_id— Optional idempotency key.payment_proof— x402 payment proof from the facilitator. Omit on the first call to receive the payment challenge.max_slippage_bps— integer — Max slippage in basis points (default 100).
Hints: read-only yes · destructive no · idempotent yes · open-world no
check_token_safetyread-onlyHoneypot / 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 other checks. This is a heuristic bytecode + simulation check, not a formal audit. Use it before trading unknown tokens, memecoins, or any contract that is absent from the official Robinhood Chain registry. It is safe to call repeatedly; no transaction is ever sent.
Parameters:
contract_address(required) — string — Token contract address (0x...).
Hints: read-only yes · destructive no · idempotent yes · open-world yes
simulate_balanceread-onlySimulate a wallet's ERC-20 balance after a hypothetical trade using eth_call state override. Read-only: no transaction is ever sent.
Parameters:
token_address(required) — string — ERC-20 contract address (0x...).holder(required) — string — Wallet address whose balance is simulated (0x...).delta(required) — number — Signed amount (negative = spend).decimals— integer — Token decimals (default 18).
Hints: read-only yes · destructive no · idempotent yes · open-world no
get_supported_assetsread-onlyList every asset in the guardrail's official Robinhood Chain registry, with its canonical contract address.
Hints: read-only yes · destructive no · idempotent yes · open-world yes
verify_audit_trailread-onlyVerify the tamper-evident audit trail for a wallet's past guardrail decisions.
Parameters:
wallet(required) — string — EVM wallet address (0x...).limit— integer — How many recent records to verify (1-1000, default 100).
Hints: read-only yes · destructive no · idempotent yes · open-world no
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.