AI agents call get_wallet_fungible_positions 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 wallet position data without modifying state or executing transactions. However, severity is elevated to 'medium' rather than 'low' because exposure of detailed DeFi portfolio positions (including protocol-specific holdings) could enable social engineering, targeted attacks, or phishing if wallet addresses are linked to identities.
From the tool's definition Tool name 'get_wallet_fungible_positions' and description 'Get fungible token positions held by a wallet' indicate data retrieval with no modification or execution capability.
Attacks that exploit this kind of access
Get fungible token (ERC-20 etc.) positions held by a wallet, including DeFi protocol positions. 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_fungible_positions: 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_fungible_positions 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_fungible_positions 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_fungible_positions. 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_fungible_positions 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 →