AI agents call get_wallet_transactions to retrieve information from Zerion without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries past transaction data from a blockchain wallet. It has no side effects, does not modify state, and does not execute code or commands. However, severity is elevated to 'medium' rather than 'low' because transaction history reveals financial activity and wallet holdings, which could enable social engineering, targeted theft, or privacy violations if an AI agent queries arbitrary wallets…
From the tool's definition Tool description states 'Get transaction history for a wallet' — a retrieval operation with no modification or execution capability. The word 'Get' and 'history' indicate read-only access to existing data.
Attacks that exploit this kind of access
Get transaction history for a wallet with rich decoded action data. It is categorised as a Read tool in the Zerion MCP Server, which means it retrieves data without modifying state.
Register the Zerion MCP server in PolicyLayer and add a rule for get_wallet_transactions: 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 Zerion. Nothing to install.
get_wallet_transactions 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 get_wallet_transactions 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 get_wallet_transactions. 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.
get_wallet_transactions is provided by the Zerion MCP server (rockyale/zerion-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 →