ComputeSage StackBench

Connect Remote server

claude mcp add --transport http stackbench https://mcp.computesage.com/mcp

{
  "mcpServers": {
    "stackbench": {
      "url": "https://mcp.computesage.com/mcp"
    }
  }
}

{
  "servers": {
    "stackbench": {
      "type": "http",
      "url": "https://mcp.computesage.com/mcp"
    }
  }
}

Settings > Connectors > Add custom connector
URL: https://mcp.computesage.com/mcp

Tools 5 found in our last check

• 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.

Details

More cloud and devops servers See all

• OxyPages

  Deploy HTML pages and built web apps (React, Vue, Vite) to a live HTTPS link from your AI agent.

• Privi Call

  One number per AI agent: route MCP calls to any agent, every call sealed in an on-chain log.

• OldWeb Diagnostics

  Public DNS, HTTPS and deployment checks, plus offline email header and delivery-log tracing.

• OldWeb Logs

  Offline log parsing, CI failures, HTTP capture analysis and bounded JSON configuration validation.

• TrainRec

  Your AI assistant logs your meals and workouts, then plans your week from what you did.

• ZeroPhase

  BUD/S prep training: read today's workout, log tasks and PST results from your agent.