What happens when an AI agent has to pay for its tools? Today, nobody knows. Open-source MCP servers run for free, and their maintainers quietly absorb the cost. The x402 protocol changes the model: a server can charge a small payment for each tool call, with no accounts or API keys needed. The plumbing works. The open question is how agents behave once tools have a price.
We put it to the test. We built a paid MCP server on Cloud and ran it end to end, live, settling real payments on a public testnet. We put the agent behind an identity provider and a policy gateway, to see what a paid tool call has to carry before anyone would run one in production. We gave the same work to two competing vendors to see who really decides which one gets bought. And we varied the system prompt, to see how much of a model's spending behaviour is a property of its instructions rather than of the request.
The result is practical guidance for maintainers: how to price a call, where the payment flow breaks, which model behaviours to expect, and whether per-call payments can realistically fund an open-source MCP server.
___________________________
Presentation Language: English
Captioning will be available for attendees in 50+ languages through Wordly. See instructions in each room to utilize captioning.
