Get the agent
AI agents call get_wallet_address to retrieve information from Agent Wallet MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves wallet address information without modifying, deleting, or executing any operations. It is a simple query operation that returns data. Even though the server manages financial assets (USDC on Solana), this specific tool only reads the wallet address and does not move funds, execute transactions, or trigger external operations.
From the tool's definition Tool name is 'get_wallet_address' and implied function is to retrieve or query wallet address information with no side effects. The description is truncated ('Get the agent') but the name and server context indicate a read-only retrieval operation.
Attacks that exploit this kind of access
Get the agent. It is categorised as a Read tool in the Agent Wallet MCP MCP Server, which means it retrieves data without modifying state.
Register the Agent Wallet MCP server in PolicyLayer and add a rule for get_wallet_address: 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 Agent Wallet MCP. Nothing to install.
get_wallet_address 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_address 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_address. 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_address is provided by the Agent Wallet MCP server (noah-ing/agent-wallet-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 →