mcpField
C
Collar Guardrail — Pre-Trade Risk Layer

Collar Guardrail — Pre-Trade Risk Layer

远程服务
collarguardrail.com金融数据03 周前更新

关于 Collar Guardrail — Pre-Trade Risk Layer

Collar Guardrail 是面向 Robinhood Chain 交易 AI Agent 的确定性交易前风险服务。它依据价格、限额、市场时段、滑点和合约安全信号检查交易,并返回可审计的判定。

主要功能

  1. 01返回允许、警告或拒绝判定
  2. 02为交易风险评分,范围为 0 至 100
  3. 03检查预言机价格和市场时段
  4. 04执行等级限额与滑点边界
  5. 05检测不安全的代币合约
  6. 06记录防篡改审计哈希

适用场景

  1. 01在执行前检查拟议交易
  2. 02阻止涉及危险合约的交易
  3. 03验证过往风险决策的完整性

MCP 相关

通过 Streamable HTTP 向 MCP 客户端提供交易评估、代币安全检查、余额模拟、资产查询和审计记录验证工具。

配置

远程服务无需本地安装。选择你使用的客户端,复制配置或使用一键安装。

服务地址https://api.collarguardrail.com/mcp-http/mcp
一键复制安装命令
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

命令在终端中运行;JSON 粘贴到对应客户端的 MCP 配置后重启。需要授权的服务会在首次连接时提示登录。

工具

6
参数类型必填说明
sidestring是「buy」或「sell」。
assetstring是资产代码,例如 NVDA、AAPL、TSLA、USDG。
amountnumber是以代币单位计的数量——不是预先计算的 USD 值。
walletstring是执行交易所用的 EVM 钱包地址(0x...)。
request_idany否可选的幂等键。
contract_addressstring是代币合约地址(0x...)。必须与该代码的官方注册表地址一致,否则交易将因疑似假代币而被拒绝。
max_slippage_bpsinteger否最大滑点,单位为基点(默认值为 100)。

详细介绍

Collar Guardrail

面向 Robinhood Chain 上 AI Agent 的确定性交易前风险层。

Collar 会在执行前评估拟议交易,并返回 allow / warn / deny,附带原因、0–100 的风险评分以及防篡改 SHA-256 审计哈希。

MCP Registry License: MIT

概述

Collar 位于自主交易 Agent 与区块链之间,作为确定性的交易前检查点。每笔拟议交易都会根据实时预言机价格、市场交易时段规则、基于等级的限额、滑点范围和合约安全信号进行评分,通过后方可继续。

结果是一个可审计的单一判定——绝非概率猜测。

端点

  • MCP 服务: https://api.collarguardrail.com/mcp-http/mcp
  • MCP 服务卡: https://api.collarguardrail.com/.well-known/mcp-server-card.json
  • Agent 卡(A2A): https://api.collarguardrail.com/.well-known/agent-card.json
  • x402 发现: https://api.collarguardrail.com/.well-known/x402.json
  • 方法论: https://api.collarguardrail.com/methodology.html
  • 实时状态: https://api.collarguardrail.com/status
  • 实时延迟(p50/p95/p99): https://api.collarguardrail.com/latency.html
  • llms.txt: https://api.collarguardrail.com/llms.txt
  • 实时终端(UI): https://collarguardrail.com

MCP 传输方式:streamable-http | 协议:2025-06-18 | 身份验证:无(固定 Tier 1)

安装

添加到 MCP 客户端配置中(Claude Desktop、Cursor、VS Code):

{
  "mcpServers": {
    "collar-guardrail": {
      "url": "https://api.collarguardrail.com/mcp-http/mcp"
    }
  }
}
Verify:

bash
curl -X POST https://api.collarguardrail.com/mcp-http/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","method":"tools/list","id":1}'
Available Tools
Tool	Purpose
evaluate_trade	Pre-trade risk check at fixed Tier 1 ($5,000 ceiling). Returns allow / warn / deny with reasons and audit hash. Honeypot findings (severity=danger) force a DENY.
evaluate_trade_paid	Same as evaluate_trade, gated by an x402 payment. Evaluated as Tier 2 ($25,000 ceiling). Call without payment_proof to receive the challenge; settle on-chain; retry with the proof.
check_token_safety	Honeypot / contract safety check for any ERC-20. When severity=danger, evaluate_trade auto-DENYs.
simulate_balance	Read-only balance simulation via eth_call state override
get_supported_assets	Official Robinhood Chain asset registry
verify_audit_trail	Verify the hash-chain integrity of past decisions
Call get_supported_assets first to resolve a symbol to its canonical
contract address. A mismatched address is treated as a fake-token attempt
and denied.

The free evaluate_trade is capped at Tier 1 ($5,000). If you need Tier 2
($25,000) without holding COLR, use evaluate_trade_paid — the on-chain
x402 payment is the credential.

Capabilities
Pricing

Chainlink oracle prices for 34+ Stock Tokens on Robinhood Chain

Uniswap V4 fallback when the oracle is stale, paused, or unconfigured

No fabricated fallback — if neither oracle nor V4 yields a price, verdict is deny

10-second V4 price cache

US Market Hours

Full US holiday calendar with observed-on-Friday/Monday shift

Early close on Thanksgiving Friday and Christmas Eve

Policy Enforcement

Tier system (REST API): 1,000 / 2,500 / 5,000 COLR → $5K / $25K / $100K limits

Per-tier rate limiting

Cluster-based rate limit and daily-loss guard (keyed on wallet fingerprint)

Slippage / MEV guard (hard 500 bps floor)

Idempotency via request_id (5-minute cache)

Global kill switch, contract mismatch detection, per-wallet blocklist

Contract Safety

Honeypot detection: bytecode scan, owner check, sell simulation via eth_call

Auto-DENY: when severity=danger, the verdict is deny regardless of
other checks — a hard stop.

GoPlus intelligence for unregistered tokens (buy/sell tax, mintable,
proxy, ownership reclaim).

Excessive tax (buy or sell > 10%) triggers an automatic deny via
GoPlus when allow_unregistered=true is passed to the request.

Auth & Infrastructure

JWT authentication via EIP-191 wallet signature (REST API)

Auth rate limiting per IP (20 req/min)

WalletConnect v2 + EIP-6963 wallet discovery

200+ token registry

Hash-chained audit trail (audit_hash + audit_seq)

Observability

Public live status page — uptime, dependency health, known issues

Public latency dashboard — p50/p95/p99 per endpoint and per MCP tool

Public methodology — how the 0–100 score is computed

Public audit-chain verification

Payments (x402)
Endpoint: POST /api/x402/analyze

Price: $0.10 USDG per call

Network: Robinhood Chain (eip155:4663)

Discovery: /.well-known/x402.json

Facilitator: Ultravioleta DAO

Listing: x402 Bazaar

No signup, no API key. Registered in the x402 Bazaar for automatic agent discovery.

Response Format
json
{
  "decision": "allow",
  "reasons": ["price source: oracle", "within tier 1 ceiling"],
  "tier": 1,
  "max_trade_usd": 5000,
  "calculated_notional_usd": 1452.30,
  "price_usd": 145.23,
  "price_source": "oracle",
  "risk_score": 12,
  "audit_hash": "sha256:...",
  "audit_seq": 12345,
  "daily_pnl_usd": 0.0
}
decision: allow / warn / deny — deny is a hard stop

reasons prefixed with ADVISORY: are non-blocking

price_source: oracle / uniswap_v4 / fallback_default / unavailable

error: if present, no verdict was produced — treat as a hard stop

Discovery Files
/.well-known/mcp-server-card.json — MCP tool schemas (canonical, flat)

/.well-known/mcp/server-card.json — alias (nested)

/.well-known/agent-card.json — A2A skills

/.well-known/x402.json — x402 payment resources

/.well-known/methodology.md — risk score methodology (agent-readable)

/.well-known/known-issues.json — public known-issues list

/methodology.html — methodology, human-readable

/mcp-card.html — rendered server card

/agent-card.html — rendered agent card

/latency.html — live latency dashboard

/status — live status page

/llms.txt — full API contract for LLM agents

/skill.md — concise skill index

/robots.txt — AI crawler allow-list

/sitemap.xml — site map

Registry Listings
Official MCP Registry: io.github.aiguardrail/backend

Smithery: search "collar"

x402 Bazaar: /api/x402/analyze

Documentation
Live Terminal (UI): https://collarguardrail.com

Agent Integration Guide: https://collarguardrail.com/agent-docs.html

MCP Server Card: https://api.collarguardrail.com/.well-known/mcp-server-card.json

Methodology: https://api.collarguardrail.com/methodology.html

Status: https://api.collarguardrail.com/status

Latency: https://api.collarguardrail.com/latency.html

Contact
X (Twitter): @collarguardrail

Disclosure
Collar is the risk layer for autonomous finance on Robinhood Chain.
Deterministic, auditable, and independent.

COLR is our own utility token, issued and operated by the Collar team.
It is not affiliated with, endorsed by, or issued by Robinhood Markets,
Inc. or any Robinhood entity. Robinhood Chain is a public blockchain we
build on — using it does not imply any relationship with Robinhood.

评论

支持 Markdown

第一次接触 MCP?

从协议是什么,到在客户端里装上第一个服务,这几条回答覆盖了大多数入门问题。

一个开放协议,规定了 AI 应用如何以统一方式连接外部工具与数据源。客户端负责与模型对话,MCP 服务负责提供工具、资源和提示模板,两者通过标准消息通信,同一个服务可以被不同客户端复用。