Malicious-wallet screen (via GoPlus, free/keyless). For any EVM address returns risk flags — cybercrime, money laundering, financial crime, darkweb, phishing, stealing/blackmail, fake KYC, mixer, sanctioned, honeypot-related, blacklist doubt and more — plus an overall malicious verdict and hit co...
AI agents call crypto.address-safety to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries external data (GoPlus malicious wallet database) and returns read-only information about address risk. It performs counterparty due diligence but makes no modifications to data, executes no code, transfers no funds, and performs no destructive actions. The returned risk assessment is advisory, meant to inform decision-making before financial interaction, not to execute those interactions itself.
From the tool's definition Tool returns risk flags and verdict for EVM addresses via GoPlus API; no write, execute, or financial operations performed. Description states it is a 'screen' and 'check' before interacting — purely informational retrieval.
Attacks that exploit this kind of access
Malicious-wallet screen (via GoPlus, free/keyless). For any EVM address returns risk flags — cybercrime, money laundering, financial crime, darkweb, phishing, stealing/blackmail, fake KYC, mixer, sanctioned, honeypot-related, blacklist doubt and more — plus an overall malicious verdict and hit count. Counterparty risk check before interacting with an address. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for crypto.address-safety: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp. Nothing to install.
crypto.address-safety is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the crypto.address-safety rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for crypto.address-safety. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
crypto.address-safety is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →