Get ERC-20 token transfer history for a wallet.
AI agents call token_transfers to retrieve information from Kxcoscan AI Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical transaction data from a blockchain explorer without modifying, executing, or deleting anything. It is a passive query operation analogous to searching or fetching records. No financial transactions are initiated by the tool itself—it only reads past transfer events.
From the tool's definition Tool name 'token_transfers' and description 'Get ERC-20 token transfer history for a wallet' indicate a query/retrieval operation.
Attacks that exploit this kind of access
Get ERC-20 token transfer history for a wallet. It is categorised as a Read tool in the Kxcoscan AI Tools MCP Server, which means it retrieves data without modifying state.
Register the Kxcoscan AI Tools MCP server in PolicyLayer and add a rule for token_transfers: 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 Kxcoscan AI Tools. Nothing to install.
token_transfers 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 token_transfers 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 token_transfers. 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.
token_transfers is provided by the Kxcoscan AI Tools MCP server (keralpatel/kxcoscan-mcp-server). 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 →