All servers · AI models & agents · Agent payments (x402) · Build & deploy
ComputeSage StackBench
com.computesage/stackbench · v0.2.1
Measured by MCP Station
| Last check | Reachable |
|---|---|
| Checked at | — |
| Check success 7 / 30 days | — |
| First-try success 30 days | — |
| Median response | — |
| Lookups 30 days | — |
| Authentication | No auth |
| MCP version | 2025-06-18 |
| Rank score | — |
| Declared risk | Read-only (all tools declare readOnlyHint) |
| Capabilities declared | tools |
| Tool definitions | 5 tools · with description 100% · input schema is an object 100% · read/destructive hints 100% |
Description written by the publisher, not verified
GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.
Connect
streamable-http · https://mcp.computesage.com/mcp
claude mcp add --transport http stackbench https://mcp.computesage.com/mcp{
"mcpServers": {
"stackbench": {
"url": "https://mcp.computesage.com/mcp"
}
}
}Tools as reported by the server
search_evidence$0.00 free search of bounded public StackBench benchmark and failure evidence; use this for evidence-only requests.check_deployment_fit$0.01 USDC on Base mainnet: check model/configuration fit against bounded StackBench capacity evidence.predict_performance$0.05 USDC: predict configuration throughput, memory, and power from bounded StackBench evidence with confidence, missing metrics, and caveats.recommend_deployment$0.25 USDC: recommend what to buy or run from bounded StackBench fit, performance, confidence, evidence, caveats, and economics only when supported.generate_launch_config$0.50 USDC: generate deterministic vLLM or llama.cpp launch templates from an exact StackBench recommendation without claiming a launch occurred.
Website · JSON · Text for agents · Registry updated 2026-08-29