CPU Performance Engineering

{
  "mcpServers": {
    "cpu-performance-engineering": {
      "command": "uvx",
      "args": [
        "cpu-perf"
      ]
    }
  }
}

claude mcp add --transport stdio cpu-performance-engineering -- uvx cpu-perf

{
  "mcpServers": {
    "cpu-performance-engineering": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "cpu-perf"
      ]
    }
  }
}

{
  "servers": {
    "cpu-performance-engineering": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "cpu-perf"
      ]
    }
  }
}

Config formats checked against the official docs on Oct 7, 2026: modelcontextprotocol.io (opens in a new tab), code.claude.com (opens in a new tab), cursor.com (opens in a new tab), code.visualstudio.com (opens in a new tab).

• lookup

  Ranked lookup over entries, sections, benchmarks, the record, notes and benchmark code, or over the sources' text…

• get_section

  The table of contents, or one section in dependency order with its benchmarks and, for the watchlist, the promotion…

• get_entry

  One entry in context: why it is listed, what to read before and after, other places it is listed, its benchmark, the…

• reading_path

  What to read, in order, for a topic, ending with the benchmark that reproduces it.

• get_benchmark

  A benchmark's claim, machine (the seven fields), results, analysis, limits, code, build and run scripts, raw output…

• editorial_record

  Why something is or is not listed: rejections by rule, claims by verdict, link notes.

• check_evidence

  A seven-field audit of a performance claim, with how the list judged similar numbers.

• read_source

  The text of one linked source, from the library or fetched now; with query, only the matching passages; with passage,…

• read_file

  Any repository file the server carries.

• library_status

  Which copy of the list is served, the daily update's state, how much of the linked material is indexed, and what is…

An MCP server that gives any AI client the whole CPU Performance Engineering list as something it can search and reason over, instead of a page it has to be pasted. Connect it to Claude Code, Codex, Claude Desktop, Cursor or VS Code and use it for your own performance work: ask questions, paste perf stat or compiler output, and the client's own model writes the answer from what the server returns, with citations back to the sources.

• cpu
• edge-ai
• inference
• arm
• awesome-list
• benchmarks
• computer-architecture
• low-latency
• optimization
• performance