$ loading_
Benchmark llm-d clusters from plain English across setup, runs, and analysis.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "llm-d-bench-mcp" yet — see the docs or source repo.
For an 8-node llm-d cluster, plan a benchmarking workflow: include what cluster information to probe, recommended test dimensions, execution order, and which MCP tools to call at each step.
A structured benchmark plan covering cluster probing, test design, execution steps, and suggested tool calls.
Run an inference benchmark on the current llm-d cluster, focusing on throughput, latency, and concurrency stability; if prerequisite information is missing, probe the cluster state first.
Returns the benchmark run process, key metric results, and an assessment of bottlenecks or abnormal nodes.
Analyze the llm-d benchmark results, summarize the main performance bottlenecks, compare differences across nodes or configurations, and suggest optimizations for the next test round.
Generates a results analysis summary with bottleneck findings, comparison conclusions, and actionable optimization recommendations.
Query Claude Code transcript analytics for cost, safety, audit, and efficiency insights.
Enable Claude Code to orchestrate multiple LLMs for coding and complex tasks.
Wrap Claude Code CLI as MCP tools for headless coding sessions and automation.
Delegate web research and image generation to ChatGPT through browser automation.
Test large MCP toolset handling and AgentCore Gateway integration in Claude Desktop.
Brainstorm with multiple LLMs before presenting an implementation plan to users.