Execute an agent capability. Requires payment via x402 (USDC on Base). Set NULLPATH_WALLET_KEY env var for payments.
AI agents use execute_agent to commit financial operations through nullpath MCP Client — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly triggers financial transactions (USDC payments on the Base blockchain) in addition to executing agent capabilities. Since Financial is the most severe category and this tool explicitly commits monetary obligations via cryptocurrency payments using a wallet key, it must be classified as Financial. Misuse could drain a user's crypto wallet or trigger unauthorized payments.
From the tool's definition Execute an agent capability. Requires payment via x402 (USDC on Base). Set NULLPATH_WALLET_KEY env var for payments.
Attacks that exploit this kind of access
Execute an agent capability. Requires payment via x402 (USDC on Base). Set NULLPATH_WALLET_KEY env var for payments. It is categorised as a Financial tool in the nullpath MCP Client MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the nullpath MCP Client MCP server in PolicyLayer and add a rule for execute_agent: 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 nullpath MCP Client. Nothing to install.
execute_agent 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 execute_agent 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 execute_agent. 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.
execute_agent is provided by the nullpath MCP Client MCP server (nullpath-labs/mcp-client). 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 →