CPU Performance Engineering — Claude Code MCP server: setup guide
Connects a CPU performance engineering knowledge base to your AI client, parsing perf stat logs, Top-down metrics, and compiler vectorisation diagnostics with cited sources.
claude mcp add cpu-perf -- uvx cpu-perfWhat CPU Performance Engineering does
The server turns a hardware optimisation repository into a local indexed reference manual for AI clients. It bundles fourteen reproducible benchmarks alongside editorial research records. During initialization, the process downloads linked documentation, vendor architecture manuals, and arXiv papers, assembling a local full-text index complete with page references.
Rather than delegating raw log analysis to an LLM, the server evaluates performance output directly. It parses perf stat tables across text, CSV, and JSON formats, computing branch miss ratios while preserving separation between P-core and E-core counters. It also flags Top-down pipeline bottlenecks and categorises loop vectorisation diagnostics from gcc and clang.
Execution happens locally over stdio via uvx cpu-perf. Because the initial launch fetches external packages and compiles the document index, client connections frequently encounter timeouts. Running uvx cpu-perf --version once in your shell warms up the environment beforehand.
What it helps with
- diagnose execution bottlenecks from raw
perf statlogs - resolve failed loop vectorisation warnings from gcc and clang
- interpret hardware performance events using official Intel, AMD, and Arm guides
- evaluate CPU pipeline stalls against Top-down methodology thresholds
Example prompts for the agent
- Inspect this
perf stat -jreport and point out where execution stalls. - clang reports
-Rpass-missedon my loop, how can I restructure the memory access? - Summarize what the architecture guide says about store forwarding stalls.
How to install CPU Performance Engineering
Platform CLI
claude mcp add cpu-perf -- uvx cpu-perfuvx runs the command named after the package; if the README names another one, use uvx --from cpu-perf <command>
Platform CLI
codex mcp add mcp -- uvx cpu-perfuvx runs the command named after the package; if the README names another one, use uvx --from cpu-perf <command>
Config file
{
"mcpServers": {
"mcp": {
"command": "uvx",
"args": [
"cpu-perf"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from cpu-perf <command>
Config file
{
"servers": {
"mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"cpu-perf"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from cpu-perf <command>
Platform CLI
gemini mcp add mcp uvx cpu-perfuvx runs the command named after the package; if the README names another one, use uvx --from cpu-perf <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about CPU Performance Engineering
How to install CPU Performance Engineering in Claude Code?
Run claude mcp add cpu-perf -- uvx cpu-perf in your terminal.
What does CPU Performance Engineering do?
It calculates processor metrics from profiler traces and validates hardware behavior against vendor engineering manuals and cited papers.
Why does the server take longer to load on its first run?
The tool downloads dependencies and indexes external papers locally. Executing uvx cpu-perf --version directly in your terminal primes the environment and prevents client timeouts.
