x402_discover
AI agents use x402_discover to commit financial operations through X402 Discovery — usually the final step of a payment, billing, or trading workflow. A call moves real money.
The x402 protocol is explicitly a payment protocol for micropayments in USDC. While 'discover' suggests a Read/query operation, within this server's context all tools are part of a financial payment flow. Sibling tools like 'register_tool_for_payment' and the server description emphasizing autonomous payment strongly suggest this tool may initiate or facilitate financial transactions.
From the tool's definition Tool name 'x402_discover' on a server described as enabling agents to 'find, evaluate, and pay for services via USDC micropayments on Base'; sibling tools include 'register_tool_for_payment' and 'x402_browse', all part of a payment-oriented ecosystem.
Attacks that exploit this kind of access
x402_discover. It is categorised as a Financial tool in the X402 Discovery MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the X402 Discovery MCP server in PolicyLayer and add a rule for x402_discover: 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 X402 Discovery. Nothing to install.
x402_discover 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 x402_discover 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 x402_discover. 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.
x402_discover is provided by the X402 Discovery MCP server (rplryan/ouroboros). 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 →