広告掲載
MCP.so
ログイン

AgentRisk M2M MCP Server認証済み注目

@Neurobyteio

リポジトリホームページ

基本情報

カテゴリ

AI とエージェント

作者

Neurobyteio

投稿者

Neurobyteio

AgentRisk M2M MCP Server について

AgentRisk M2M 🛡️ The Security & Trust Layer for Autonomous Agents on Base. Stop letting your trading agents get rekt by stealth honeypots, dynamic sell-blocks, and rugpulls that pass every static check. ⚡ The Problem

#base#security#mcp#web3#ai-agents#trading-bots#x402#honeypot-detection#defi-security#uniswap#aerodrome

AgentRisk M2M MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "agentrisk": {
      "command": "npx",
      "args": [
        "-y",
        "agentrisk-mcp"
      ]
    }
  }
}

AgentRisk M2M MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is AgentRisk?

A pay-per-call security and trust layer for AI agents trading tokens on Base. Combines honeypot detection, deployer history, and on-chain verification with a live sell simulation across every DEX architecture on Base (Uniswap V2/V3/V4, Aerodrome) — catching dynamic honeypots that pass static checks but can't actually be sold.

How to use AgentRisk?

Call it directly via GET /scan?token=<address>, or install a native package for your framework: agentrisk-mcp (MCP), @agentrisk/plugin-elizaos, @agentrisk/langchain, @agentrisk/ai-sdk, @agentrisk/agentkit, or the agentriskm2m Python SDK. Both direct and package calls are gated by x402 (0.15 USDC per call, settled on Base via Coinbase's CDP facilitator). 3 free scans per wallet, no signup.

Key features of AgentRisk

  • Live sell simulation across every DEX architecture on Base — not just static code checks
  • Direct on-chain verification (ownership, pausability, LP-burn) plus GoPlus Security and DexScreener cross-checks
  • Policy Engine — pass custom thresholds (max_risk, require_lp_lock) for an explicit ALLOW/BLOCK
  • Cryptographically signed receipts and a /verify endpoint so one agent can trust another's cached result without re-scanning
  • Exit Liquidity Score — price impact at $100/$1K/$10K, since risk depends on position size
  • x402 micropayments via Coinbase's CDP facilitator — no API keys, no subscriptions
  • Structured shouldExecute decision object designed for autonomous agents

Use cases of AgentRisk

  • Pre-trade risk gate for autonomous trading agents before executing a swap
  • Honeypot and dynamic rug-pull screening for newly deployed Base tokens
  • Verifiable, cacheable risk data one agent can share with another via signed receipts

よくある質問

1

Where is the source code?

https://github.com/Neurobyteio/agentrisk

2

Does AgentRisk require an API key?

No. Access is metered per-call via x402 (0.15 USDC per scan on Base Mainnet). 3 free scans per wallet, no signup.

3

Which network does AgentRisk support?

Base Mainnet only (chain id 8453) — by design, for deep, specialized coverage rather than shallow multi-chain support.

コメント

「AI とエージェント」の他のコンテンツ

AON — Agent Offer Network

AON

AON MCP connects AI agents to real, buyable products and services with live pricing and tracked links—enabling builders to earn developer revenue share from attributed clicks and conversions.

2
L

Legion MCP

faulkj

MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.

1

Hypnothera

La-Salida

Agent skill: turn what your AI assistant knows about you into a personalized hypnosis session on hypnothera.ai

Nova Data Analytics

nova-data-analytics

Amazon Seller Central MCP server. Connect Seller Central, Vendor Central and Amazon Ads to Claude, ChatGPT, Gemini or Cursor, and ask for net profit per SKU with your own COGS, VAT and FBM shipping costs, PPC down to the

Phi Longevity PRISM

Phi Longevity

Guideline-cited lab-results analysis for people managing type 2 diabetes, kidney disease, lupus and cancer survivorship. Flags tests that are missing or overdue (ADA, KDIGO, NCCN — each cited) and returns questions to br

広告掲載