Official MCP RegistryListed
ComputeSage StackBench
GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.
First seen 2 Oct 2026. Evidence as of 5 Oct 2026.
5
Tools
From an anonymous probe
1
Source listings
Each with its own history
0
Recorded changes
Since first seen
Tools
| Tool | Description | Behaviour |
|---|---|---|
| check_deployment_fit | $0.01 USDC on Base mainnet: check model/configuration fit against bounded StackBench capacity evidence. | Read-only |
| generate_launch_config | $0.50 USDC: generate deterministic vLLM or llama.cpp launch templates from an exact StackBench recommendation without claiming a launch occurred. | Read-only |
| predict_performance | $0.05 USDC: predict configuration throughput, memory, and power from bounded StackBench evidence with confidence, missing metrics, and caveats. | Read-only |
| recommend_deployment | $0.25 USDC: recommend what to buy or run from bounded StackBench fit, performance, confidence, evidence, caveats, and economics only when supported. | Read-only |
| search_evidence | $0.00 free search of bounded public StackBench benchmark and failure evidence; use this for evidence-only requests. | Read-only |
Change history
No changes since the first observation. The first snapshot is the baseline.
| Source | Listing | First seen | Last seen | Versions |
|---|---|---|---|---|
| Official MCP Registry | com.computesage/stackbench | 2 Oct 2026 | 5 Oct 2026 | 1 |