Search / com.computesage/stackbench
protogridR0· no sign-inGPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.
v0.2.1 · active · website · descriptor JSON · versions
{
"mcpServers": {
"stackbench": {
"type": "http",
"url": "https://mcp.computesage.com/mcp"
}
}
}claude mcp add --transport http stackbench https://mcp.computesage.com/mcp[mcp_servers.stackbench]
url = "https://mcp.computesage.com/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"stackbench": {
"type": "remote",
"url": "https://mcp.computesage.com/mcp",
"enabled": true
}
}
}{
"mcpServers": {
"stackbench": {
"type": "http",
"url": "https://mcp.computesage.com/mcp"
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=stackbench&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLmNvbXB1dGVzYWdlLmNvbS9tY3AifQ%3D%3D"
}{
"servers": {
"stackbench": {
"type": "http",
"url": "https://mcp.computesage.com/mcp"
}
}
}{
"mcpServers": {
"stackbench": {
"httpUrl": "https://mcp.computesage.com/mcp"
}
}
}extensions:
"stackbench":
enabled: true
name: "stackbench"
type: streamable_http
uri: "https://mcp.computesage.com/mcp"
timeout: 300
protocol.modernsupports 2026-07-28 (server/discover)protocol.statelessanswers without a sessionprotocol.transportstreamable HTTPprotocol.list_ttltools/list declares ttlMs 0, so clients re-fetch it on every useauth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptionsevery tool has a descriptiontools.description_lengthdescriptions are concisetools.schemasevery tool has an object input schematools.annotations5 of 5 tools declare readOnlyHint or destructiveHinttools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHinttools.token_costabout 2,605 tokens to load every tooltools.api_dumptools are not a one-to-one API dumpstability.changesno tool changes in 30 daysstability.rug_pullno tool changed its meaning under the same namedeps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI packageNo tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+dns-namespace +website +reachable +uptime-99% ~updated-51d-ago -no-repository
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://mcp.computesage.com/mcp streamable-http | none | yes | 99% | 643 ms | 2026-07-28 | 2026-10-19 |
check_deployment_fitread-only | $0.01 USDC on Base mainnet: check model/configuration fit against bounded StackBench capacity evidence. |
generate_launch_configread-only | $0.50 USDC: generate deterministic vLLM or llama.cpp launch templates from an exact StackBench recommendation without claiming a launch occurred. |
predict_performanceread-only | $0.05 USDC: predict configuration throughput, memory, and power from bounded StackBench evidence with confidence, missing metrics, and caveats. |
recommend_deploymentread-only | $0.25 USDC: recommend what to buy or run from bounded StackBench fit, performance, confidence, evidence, caveats, and economics only when supported. |
search_evidenceread-only | $0.00 free search of bounded public StackBench benchmark and failure evidence; use this for evidence-only requests. |
Schemas: list_tools.
{
"name": "com.computesage/stackbench",
"title": "ComputeSage StackBench",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://mcp.computesage.com/mcp",
"type": "streamable-http"
}
],
"version": "0.2.1",
"websiteUrl": "https://computesage.com/mcp",
"description": "GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs."
}