Send USDC to another Solana address. This executes a real transaction on Solana devnet.
AI agents use send_usdc to commit financial operations through Agent Wallet MCP — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool moves USDC (a stablecoin with real monetary value) to another address by executing a blockchain transaction. Even though it operates on Solana devnet (a test network), the description explicitly says 'real transaction' and USDC transfers constitute financial operations that move funds irreversibly. Blockchain transactions are generally irreversible, making misuse potentially costly.
From the tool's definition 'Send USDC to another Solana address. This executes a real transaction on Solana devnet.'
Attacks that exploit this kind of access
Send USDC to another Solana address. This executes a real transaction on Solana devnet. It is categorised as a Financial tool in the Agent Wallet MCP MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Agent Wallet MCP server in PolicyLayer and add a rule for send_usdc: 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.
send_usdc is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the send_usdc 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 send_usdc. 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.
send_usdc 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 →