ComputeSage StackBench is answering right now. Last checked 4 min ago. It exposes 5 tools.
GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.
Today is the operative word: we check ComputeSage StackBench every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 4 min ago.
claude mcp add stackbench --transport http https://mcp.computesage.com/mcp
{
"mcpServers": {
"stackbench": {
"url": "https://mcp.computesage.com/mcp"
}
}
}
[mcp_servers.stackbench]
url = "https://mcp.computesage.com/mcp"
{
"mcpServers": {
"stackbench": {
"url": "https://mcp.computesage.com/mcp"
}
}
}
{
"mcpServers": {
"stackbench": {
"url": "https://mcp.computesage.com/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
check_deployment_fit
search_evidence
generate_launch_config
predict_performance
recommend_deployment
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.computesage.com/mcp | streamable-http | answering | 471 ms | 4 min ago |
Remote MCP server for RunComfy Serverless API (ComfyUI): deployments and async inference.
MCP server for InsForge BaaS — database, storage, edge functions, and deployments
Local-first LLM deployment planner: GPU/VRAM sizing, cost and latency, with provenance
Advisory AOS agent health scan before deployment (manifest, services, immune loop, evidence).
Cloud cost visibility and savings recommendations grounded in your actual AWS, GCP and Azure bill.
Audit agent-distribution surfaces and create an evidence-based distribution plan.
Deploy static sites from AI agents: deploy_site publishes files and returns a live URL in seconds.
Cloud architecture and migration planning with costs, controls, evidence, and deployable IaC.
Answers built from our own checks of this server.