Engineering brief
X402 Isn't Ready: The State of Agentic Payments in 2025
At a glance
- Relevance
- Practical value
- Warnings
- None
Apify's CEO just showed why X402 agentic payments aren't production-ready yet. Double-spending risks, conflicting HTTP status codes with MCP, and no batch settlement until months from now.
Agentic payments are inevitable but current infrastructure costs more than it delivers.
Summary
Apify CEO Jan Cerny argues that X402, like MCP before it, is not production-ready despite significant industry momentum. The protocol forces HTTP 402 status codes that conflict with MCP's 401, requiring duplicate API hosts per payment provider—an anti-pattern for engineering teams.
The double-spending problem remains unsolved: clients can sign multiple payment requests before blockchain settlement, creating risk for service providers. Coinbase's new batch settlement scheme looks promising but isn't implemented yet, and the ecosystem lacks basic tooling like wallet management for agents.
Apify's workaround—a separate AGI endpoint where agents buy prepaid tokens—shows the current state of the art. It's functional but clunky, requiring two blockchain transactions for variable billing. The total monthly transaction volume is only $1M, signaling a market that is real but tiny.
The real signal is that agentic payments infrastructure is where MCP was a year ago: lots of hype, multiple competing standards, and a long road to production maturity. Teams should plan for experimentation, not deployment.
Watch the video
This video is blocked due to your privacy settings. To watch this video, please accept YouTube marketing cookies.
Related breakdowns
ACP: The protocol that could finally decouple clients from agent harnesses
ACP standardizes how clients talk to AI agents. Early demos show any client controlling any harness. Adoption is the open question.
AI agents fail without organizational context: the case for context engineering
AI agents are smart but ignorant of your organization's history. Context engineering solves the gap between code that compiles and code that works.
LLM inference is a memory problem, not a compute problem
Inference cost is the hidden operational tax on AI products. This workshop breaks down the KV cache bottleneck, model vs. serving optimisations, and when VLM…
Get TL;DW
Too Long; Didn't Watch.
A concise breakdowns of the AI and devtools videos that actually matter for engineering leaders.
Free. Weekly. No hype.
Video and thumbnails remain the property of their respective creators. tldw.news provides editorial analysis, commentary, and discovery links to original content.