perfetto-mcp-rs

English | 简体中文

An MCP server for analyzing
Perfetto traces with LLMs. Point Claude Code (or any
MCP client) at a .perfetto-trace / .pftrace file and query it with
PerfettoSQL.

Backed by trace_processor_shell — downloaded automatically on first run, no
manual Perfetto install required.

Works best with agentic MCP clients (Claude Code, Codex, Claude Desktop, Cursor)
that can chain multi-turn tool calls. Non-agentic clients will see the same
tools but won't be able to follow the error-message nudges that steer the
LLM through the typical load_trace → list_tables → list_table_structure →
execute_sql flow.

Navigate agents toward the right PerfettoSQL stdlib modules — the analysis SQL is always the agent's own.

Quick install

Linux / macOS / Windows (Git Bash, MSYS2, Cygwin):

curl -fsSL https://raw.githubusercontent.com/0xZOne/perfetto-mcp-rs/main/install.sh | sh

Windows (PowerShell):

irm https://raw.githubusercontent.com/0xZOne/perfetto-mcp-rs/main/install.ps1 | iex

Both installers drop the prebuilt binary into ~/.local/bin (or
%USERPROFILE%\.local\bin on Windows), add it to your user PATH if needed,
and — if Claude Code and/or Codex are installed — register it automatically.
Restart Claude Code or start a new Codex session to pick it up.

Claude scope: registration defaults to --scope user (available from any
directory). For a project-local install, set SCOPE=local (or project) and
run the script from that project's directory:

SCOPE=local bash -c 'curl -fsSL https://raw.githubusercontent.com/0xZOne/perfetto-mcp-rs/main/install.sh | sh'

PowerShell equivalent: $env:SCOPE = 'local'; irm ... | iex. Codex has no
scope concept and ignores this variable.

Supported platforms: linux amd64/arm64, macOS amd64/arm64, Windows amd64.
If you'd rather not run a script, grab the binary directly from the
releases page. Release
assets are named perfetto-mcp-rs-<platform> (e.g. perfetto-mcp-rs-linux-amd64);
rename or address the downloaded file explicitly when invoking install, and
on Unix mark it executable first (chmod +x) — the subcommand refuses
non-executable paths to avoid writing a broken MCP entry. Example:

# Linux amd64 example — adjust the asset name for your platform.
curl -fsSL -o perfetto-mcp-rs \
  https://github.com/0xZOne/perfetto-mcp-rs/releases/latest/download/perfetto-mcp-rs-linux-amd64
chmod +x perfetto-mcp-rs
./perfetto-mcp-rs install --scope user --binary-path "$PWD/perfetto-mcp-rs"

Upgrade

Re-run the same install command — it pulls the latest release, safely
overwrites the existing binary (with Windows file-lock retry), and
re-registers the MCP server with Claude Code / Codex idempotently.

Pin to a specific version with the VERSION env var:

VERSION=v0.7.0 curl -fsSL https://raw.githubusercontent.com/0xZOne/perfetto-mcp-rs/main/install.sh | sh

No auto-update daemon — upgrades are explicit.

Uninstall

Symmetric one-liner per platform. Deregisters from Claude Code and Codex,
removes the binary, and deletes the cached trace_processor_shell. Idempotent
— safe to run if any step was already done by hand.

Linux / macOS / Windows (Git Bash, MSYS2, Cygwin):

curl -fsSL https://raw.githubusercontent.com/0xZOne/perfetto-mcp-rs/main/uninstall.sh | sh

Windows (PowerShell) — close Claude Code, Codex, or anything else using the .exe first:

irm https://raw.githubusercontent.com/0xZOne/perfetto-mcp-rs/main/uninstall.ps1 | iex

Scoped installs (local / project): claude stores local/project entries
keyed by project directory, so uninstall must use the same SCOPE AND run
from that directory. Omitting this leaves the scoped Claude entry behind while
the wrapper still removes the binary and cache:

# Ran `SCOPE=local bash install.sh` in ~/work/foo earlier? Then:
cd ~/work/foo
SCOPE=local bash -c 'curl -fsSL https://raw.githubusercontent.com/0xZOne/perfetto-mcp-rs/main/uninstall.sh | sh'

PowerShell equivalent: cd <original-project-dir>; $env:SCOPE = 'local'; irm ... | iex.

$INSTALL_DIR (default ~/.local/bin) is not removed from your PATH:

• Linux / macOS — the installer only prints a PATH hint; if you added
  it to your shell rc, remove that line manually.
• Windows — the installer writes $INSTALL_DIR into your user PATH
  (HKCU\Environment); remove it via System Properties → Environment Variables
  if you want it gone.

Other tools may still depend on this directory, which is why uninstall leaves
it in place.

Tools

Typical flow depends on trace type:

• Chrome traces: load_trace → dedicated chrome_* tools
  (chrome_scroll_jank_summary, chrome_page_load_summary,
  chrome_main_thread_hotspots, chrome_startup_summary,
  chrome_web_content_interactions) → execute_sql for deeper analysis
  on the returned rows.
• Other traces: load_trace → list_tables / list_table_structure
  for schema discovery → execute_sql for queries. Call
  list_stdlib_modules as an auxiliary when stdlib modules might cover
  your analysis (Android, generic modules like slices.with_context).

Example

Ask Claude Code or Codex something like:

Load ~/traces/scroll_jank.pftrace and tell me the top scroll jank causes.

Claude will call load_trace, then issue a query like:

INCLUDE PERFETTO MODULE chrome.scroll_jank.scroll_jank_v3;
SELECT cause_of_jank, COUNT(*) AS n
FROM chrome_janky_frames
GROUP BY cause_of_jank
ORDER BY n DESC;

Manual MCP client configuration

If the installer's auto-registration doesn't apply to your client:

Codex:

codex mcp add perfetto-mcp-rs -- /absolute/path/to/perfetto-mcp-rs

JSON-based clients (e.g. Claude Code, Claude Desktop, Cursor):

{
  "mcpServers": {
    "perfetto-mcp-rs": {
      "command": "/absolute/path/to/perfetto-mcp-rs"
    }
  }
}

Configuration

CLI flags:

Build from source

Requires a Rust toolchain and protoc (Protocol Buffers compiler):

# Ubuntu/Debian
sudo apt install -y protobuf-compiler
# macOS
brew install protobuf
# Windows
choco install protoc

Then:

git clone https://github.com/0xZOne/perfetto-mcp-rs
cd perfetto-mcp-rs
cargo build --release
# Binary at target/release/perfetto-mcp-rs

Development

cargo test          # unit tests
cargo clippy        # lint
cargo fmt           # format

License

Dual-licensed under either of Apache License, Version 2.0 or
MIT license at your option. Contributions are accepted under
the same terms.