Make an HTTP request to a URL that may require payment. If the server
AI agents use pay.fetch to commit financial operations through Thebuyside X402 Agent — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool can autonomously initiate financial transactions (cryptocurrency payments on Base or Solana) as part of fetching a resource. Even though it also performs an HTTP request (Read/Execute behavior), the dominant and most severe risk is Financial — an AI agent could misuse this to spend funds without explicit per-call user authorization.
From the tool's definition 'pay metered APIs', 'may require payment', 'without the user wiring payments themselves' — the tool autonomously makes HTTP requests that can trigger payment flows on Base or Solana blockchains
Attacks that exploit this kind of access
Make an HTTP request to a URL that may require payment. If the server. It is categorised as a Financial tool in the Thebuyside X402 Agent MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Thebuyside X402 Agent MCP server in PolicyLayer and add a rule for pay.fetch: 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 Thebuyside X402 Agent. Nothing to install.
pay.fetch 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 pay.fetch 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 pay.fetch. 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.
pay.fetch is provided by the Thebuyside X402 Agent MCP server (jaysperspective/thebuyside-x402-agent). 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 →