Token honeypot & rug-pull risk screen (via GoPlus, free/keyless). For an ERC-20 on any EVM chain, returns honeypot flag, buy/sell tax, open-source/proxy/mintable status, hidden-owner / take-back-ownership / selfdestruct / external-call risks, blacklist/whitelist/anti-whale flags, holder count, an...
AI agents call crypto.token-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 and retrieves token metadata and risk indicators from GoPlus; it does not execute trades, transfer funds, approve tokens, or perform any on-chain transactions. It is a passive information-gathering tool for pre-trade analysis. Although the server context involves crypto and financial instruments, the tool itself only performs Read operations (data retrieval).
From the tool's definition Tool returns risk screening data: honeypot flag, buy/sell tax, token properties (open-source/proxy/mintable), holder concentration, blacklist/whitelist flags.
Attacks that exploit this kind of access
Token honeypot & rug-pull risk screen (via GoPlus, free/keyless). For an ERC-20 on any EVM chain, returns honeypot flag, buy/sell tax, open-source/proxy/mintable status, hidden-owner / take-back-ownership / selfdestruct / external-call risks, blacklist/whitelist/anti-whale flags, holder count, and owner/creator concentration. Essential pre-trade safety check. 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.token-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.token-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.token-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.token-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.token-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 →