We and selected third parties use cookies or similar technologies for technical purposes and, with your consent, to analyze how the site is used.

You can freely give, refuse or withdraw your consent at any time.

CPU Performance Engineering

MCP server by usamahz

Search a vetted CPU performance reading list, benchmarks and cited source passages, and analyze perf stat and compiler output.

Runs locally (Runs on your machine: its page has the install command)Runs with uvx

Install CPU Performance Engineering

Runs on your machine. Your client starts it with this command:

uvx cpu-perf

Needs uv (Python) on your computer. The setup steps below show where the command goes in each client.

Share this server

Opens this page, with the install command and setup steps.

mcp.tc/i/cpu-performance-engineering

About

Gives an AI client a searchable copy of the CPU Performance Engineering reading list: entries and their reasons, the watchlist, the editorial record, fourteen benchmarks, and the papers, manuals and documentation the list links to. Answers carry citations back to the sources, with page numbers.

You can also paste perf stat output, top-down metrics, gcc or clang vectorization remarks, or disassembly, and the server parses them and routes you to the relevant sources.

What you can do

  • Search the CPU performance reading list and its editorial record
  • Retrieve cited passages from papers, manuals and documentation
  • Parse perf stat output and compute ratios such as IPC and miss rates
  • Read top-down level 1 and 2 metrics with cited thresholds
  • Explain gcc -fopt-info and clang -Rpass vectorization remarks
  • Analyze objdump, gdb and perf annotate assembly
  • Browse benchmark claims, machines, results and code

Tools

Local servers list their tools once they’re running, and this one doesn’t publish its list in advance. Your client shows them after you add it.

Example prompts

  • Why does my multithreaded counter stop scaling past two threads?

  • Here is my perf stat output; where is the time going?

  • gcc says not vectorized: complicated access pattern; what do I change?

  • Give me a reading path for NUMA, ending with something I can run.

Set up

Every client starts CPU Performance Engineering on your machine with the same command. Pick yours; the page remembers your choice.

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport stdio cpu-performance-engineering -- uvx cpu-perf
  1. Start Claude Code and type /mcp. cpu-performance-engineering should show as connected.

Add --scope user to make it available in every project.

Claude Desktop

  1. Open Settings → Developer → Edit Config. It opens claude_desktop_config.json. Add:
claude_desktop_config.json
{
  "mcpServers": {
    "cpu-performance-engineering": {
      "command": "uvx",
      "args": [
        "cpu-perf"
      ]
    }
  }
}
  1. Save the file and restart Claude Desktop.

Needs uv (Python) on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.

Cursor

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

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

Needs uv (Python) on your computer.

VS Code

Or from a terminal:

code --add-mcp '{"name":"cpu-performance-engineering","type":"stdio","command":"uvx","args":["cpu-perf"]}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "cpu-performance-engineering": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "cpu-perf"
      ]
    }
  }
}

Needs uv (Python) on your computer.

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "cpu-performance-engineering": {
      "command": "uvx",
      "args": [
        "cpu-perf"
      ]
    }
  }
}
  1. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf.

Codex

codex mcp add cpu-performance-engineering -- uvx cpu-perf

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.cpu-performance-engineering]
command = "uvx"
args = ["cpu-perf"]

Needs uv (Python) on your computer.

Gemini CLI

gemini mcp add cpu-performance-engineering uvx cpu-perf

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients that start local servers accept this shape:

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

Zed puts servers under context_servers in its settings, with the same command, args and env fields.

Needs uv (Python) on your computer.

Embed

Show CPU Performance Engineering in a README or on your site. Each embed links to this page, uses the server’s own install command, and sets no cookies. How embeds work

The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.

README badge

Badge preview, lightBadge preview, dark
Markdown
[![CPU Performance Engineering on mcp.tc](https://mcp.tc/i/cpu-performance-engineering/badge.svg)](https://mcp.tc/i/cpu-performance-engineering)
HTML
<a href="https://mcp.tc/i/cpu-performance-engineering"><img src="https://mcp.tc/i/cpu-performance-engineering/badge.svg" alt="CPU Performance Engineering on mcp.tc" height="20"></a>

It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.

Website card

HTML
<script src="https://mcp.tc/w/cpu-performance-engineering.js" async></script>

The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.

iframe

HTML
<iframe src="https://mcp.tc/embed/cpu-performance-engineering" title="CPU Performance Engineering on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.

JSON

The listing as data for your own pages and tools: name, tagline, install command, tools and the “Add to” links. Any site can read it (CORS is open).

https://mcp.tc/i/cpu-performance-engineering.json

What each field means

AI prompt

Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the CPU Performance Engineering card to your site.

Markdown
Add the mcp.tc card for CPU Performance Engineering, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.

Put this tag where the card should appear. The card renders right before it:

```html
<script src="https://mcp.tc/w/cpu-performance-engineering.js" async></script>
```

To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.

```html
<div data-mcptc="cpu-performance-engineering"><a href="https://mcp.tc/i/cpu-performance-engineering">CPU Performance Engineering on mcp.tc</a></div>
```

Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.

If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).

For a README or other Markdown docs, use the badge instead:

```markdown
[![CPU Performance Engineering on mcp.tc](https://mcp.tc/i/cpu-performance-engineering/badge.svg)](https://mcp.tc/i/cpu-performance-engineering)
```

Reference: https://mcp.tc/embed

Change history

This server runs on your computer, so we follow its PyPI package: each new version shows up here, with edits by its owner.

Follow CPU Performance Engineering and we’ll email you when something changes.

  1. , Automatic check

    Tracking started: version 0.1.1.

FAQ

Can I paste mcp.tc/i/cpu-performance-engineering into my MCP client?

No. CPU Performance Engineering runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is uvx cpu-perf.

Does CPU Performance Engineering need an API key?

No. It doesn’t declare any keys or environment variables. It runs with your user account’s permissions, so check what its tools can reach.

Is CPU Performance Engineering a remote or a local server?

Local. Your client starts it as a process on your computer with uvx cpu-perf, which needs uv (Python).

What can CPU Performance Engineering do?

You can search the CPU performance reading list and its editorial record, retrieve cited passages from papers, manuals and documentation and parse perf stat output and compute ratios such as IPC and miss rates.

Which clients can use it?

Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.

Does mcp.tc track changes to CPU Performance Engineering?

Partly. It runs on your computer, so we follow its PyPI package: its History tab shows each new version and edits by its owner. Follow the listing to get an email when it changes.

Who wrote this page?

mcp.tc’s robot read CPU Performance Engineering’s public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

mcp.tc isn’t affiliated with usamahz. This page was built from CPU Performance Engineering’s public metadata, last checked on 12 Oct 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.