AI agents call get_app_positions to retrieve information from Zapper 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 existing DeFi position data without modifying state, executing code, or moving assets. It is a read-only information retrieval operation on a portfolio API, similar to the sibling tool 'get_token_balances'. The low severity reflects that exposure of portfolio position data has limited blast radius—it reveals information but cannot trigger transactions or destructive actions.
From the tool's definition Tool name 'get_app_positions' and description explicitly states it retrieves 'DeFi app positions' (Aave lending, Uniswap LP, staking, etc.) for querying protocol exposure.
Attacks that exploit this kind of access
DeFi app positions only (Aave lending, Uniswap LP, staking, etc.). Use when the question is about protocol exposure:. It is categorised as a Read tool in the Zapper MCP Server, which means it retrieves data without modifying state.
Register the Zapper MCP server in PolicyLayer and add a rule for get_app_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 Zapper. Nothing to install.
get_app_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_app_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_app_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_app_positions is provided by the Zapper MCP server (mehdi-loup/zapper-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 →