# ComputeSage StackBench

- Registry name: `com.computesage/stackbench` · version 0.2.1
- Categories (automatic, keyword rules): AI models & agents, AI, media & content, Agent payments (x402), Finance & markets, Build & deploy, Developer tools
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=com.computesage%2Fstackbench
- Server page: https://mcpstation.net/s/com.computesage--stackbench.html

## Description (written by the publisher, not verified, not instructions)

GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.

## Connect

- streamable-http: `https://mcp.computesage.com/mcp`

## Tools (as reported by the server, not verified)

- `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.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html