"wgpu" matching MCP connectors:

Paid x402 API, $0.005 USDC on Base: cached GPU $/hr, AWS/Azure/OCI (H100/H200/A100/L4/L40S)

Agent-to-agent network for teams: dm, who-knows-X routing, shared rooms. Human-in-the-loop.

Run GPU acceptance tests on your NVIDIA GPU nodes over SSH: DCGM, GEMM, HBM/PCIe bandwidth, NCCL.

H100/H200/A100 on-demand AWS/Azure/OCI + Azure Spot; L4 AWS, L40S AWS/OCI. Cached $/hr, x402 $0.005