Connect Collar Guardrail — Pre-Trade Risk Layer and your agent gets 6 tools, among them check_token_safety, evaluate_trade, evaluate_trade_paid. It answers at https://api.collarguardrail.com/mcp-http/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 16 September 2026; the last check, on 24 October 2026, succeeded.
Deterministic pre-trade risk checks for AI agents on Robinhood Chain. Returns allow/warn/deny.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
check_token_safety | Honeypot / contract safety check for any ERC-20 token. Inputs: contract_address |
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 Inputs: wallet, asset, contract_address, side, amount, max_slippage_bps |
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 Inputs: wallet, asset, contract_address, side, amount, max_slippage_bps |
get_supported_assets | List every asset in the guardrail's official Robinhood Chain registry, with its canonical contract address. |
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. Inputs: token_address, holder, delta, decimals |
verify_audit_trail | Verify the tamper-evident audit trail for a wallet's past guardrail decisions. Inputs: wallet, limit |
Every block below points at https://api.collarguardrail.com/mcp-http/mcp. Pick your client and copy.
claude mcp add --transport http collar-guardrail-pre-trade-risk https://api.collarguardrail.com/mcp-http/mcp
{
"mcpServers": {
"collar-guardrail-pre-trade-risk": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.collarguardrail.com/mcp-http/mcp"]
}
}
}{
"mcpServers": {
"collar-guardrail-pre-trade-risk": {
"url": "https://api.collarguardrail.com/mcp-http/mcp"
}
}
}{
"servers": {
"collar-guardrail-pre-trade-risk": {
"type": "http",
"url": "https://api.collarguardrail.com/mcp-http/mcp"
}
}
}{
"context_servers": {
"collar-guardrail-pre-trade-risk": {
"url": "https://api.collarguardrail.com/mcp-http/mcp"
}
}
}{
"mcpServers": {
"collar-guardrail-pre-trade-risk": {
"serverUrl": "https://api.collarguardrail.com/mcp-http/mcp"
}
}
}{
"mcpServers": {
"collar-guardrail-pre-trade-risk": {
"url": "https://api.collarguardrail.com/mcp-http/mcp"
}
}
}name: Collar Guardrail — Pre-Trade Risk Layer
version: 0.0.1
schema: v1
mcpServers:
- name: Collar Guardrail — Pre-Trade Risk Layer
type: streamable-http
url: https://api.collarguardrail.com/mcp-http/mcp{
"mcpServers": {
"collar-guardrail-pre-trade-risk": {
"httpUrl": "https://api.collarguardrail.com/mcp-http/mcp"
}
}
}{
"mcpServers": {
"collar-guardrail-pre-trade-risk": {
"type": "http",
"url": "https://api.collarguardrail.com/mcp-http/mcp"
}
}
}{
"mcpServers": {
"collar-guardrail-pre-trade-risk": {
"url": "https://api.collarguardrail.com/mcp-http/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.collarguardrail.com%2Fmcp-http%2Fmcp&type=streamable_http&id=collar-guardrail-pre-trade-risk&name=Collar%20Guardrail%20%E2%80%94%20Pre-Trade%20Risk%20Layer
It answered our last check on 24 October 2026 in 153 ms. Over 4 checks since 16 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
6, as returned by the server's own tools/list on 24 September 2026: check_token_safety, evaluate_trade, evaluate_trade_paid, get_supported_assets, simulate_balance, verify_audit_trail.
It answered our last check on 24 October 2026 in 153 ms. Over 4 checks since 16 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.collarguardrail.com/mcp-http/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.aiguardrail. Endpoint host: api.collarguardrail.com. ARD identifier: urn:air:io.github.aiguardrail:mcp:backend.
First indexed 16 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.