What is etw-mcp CLAUDE.md?

A project guide for an MCP server that uses Windows xperf.exe to analyse ETW trace files, which record system and application activity.

Use it to load and manage traces, inspect symbols, diagnose symbol problems, and analyse CPU samples and hot functions.

It explains the server layout, trace lifecycle, and tool registration so agents can work safely with Windows performance traces.

How nijosmsft/etw-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to nijosmsft/etw-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/nijosmsft/etw-mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/nijosmsft/etw-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nijosmsft/etw-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/nijosmsft/etw-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/nijosmsft/etw-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nijosmsft/etw-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nijosmsft/etw-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nijosmsft/etw-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,145 This file is loaded in full into every session.

When invoked 4,145 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.04145	$0.04145
Opus 5.5	$0.01658	$0.01658
Sonnet 5.5	$0.00829	$0.00829
Haiku 4.5	$0.00415	$0.00415

Measured 2mo ago against content hash 6a9a17a82aff, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

etw-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code (and other AI assistants) when working on the etw-mcp source. For end-user docs (install, MCP config, tool list), see README.md.

What this repo is

An MCP server that wraps xperf.exe so AI assistants can analyze Windows WPR/ETW traces (.etl). Python 3.11+, packaged with uv, served over stdio via FastMCP. Windows-only — every analysis tool ultimately runs xperf as a subprocess.

Layout

src/etw_analyzer/
  server.py              ← entry point: imports each tools.* module to register @mcp.tool()s, then mcp.run("stdio")
  app.py                 ← single FastMCP instance ("etw-trace-analyzer") + server instructions
  trace_state.py         ← TraceData dataclass + registry (make_trace_id, register/get/require_trace, list_loaded_trace_ids)
  tools/                 ← one module per tool group; each calls @mcp.tool() at import time
    trace_mgmt.py        ← list_traces, load_trace, list_loaded_traces, unload_trace, trace_info, check_symbols, resolve_symbols
    symbol_diagnostics.py ← diagnose_symbol_load, clean_stale_symbol_files
    cpu_sampling.py      ← get_cpu_samples, get_hot_functions
    per_cpu.py           ← get_per_cpu_summary, get_cpu_timeline
    stack_analysis.py    ← get_hot_stacks, get_function_callers, walk_stack, count_stacks, butterfly_chain
    dpc_isr.py           ← get_dpc_summary, get_dpc_per_cpu
    context_switch.py    ← get_lock_contention
    memory.py            ← get_memory_pools
    system_info.py       ← get_sysconfig, get_process_info, get_diskio_summary, get_trace_stats
    compare.py           ← compare_traces
    summary.py           ← analyze, export_analysis
    capture_profiles.py  ← list_capture_profiles, get_capture_profile, get_capture_commands, get_capture_instructions
  profiles/              ← bundled .wprp capture profiles (cpu, cpu_dpc_isr, network, network_minimal, network_packets, xdp_cpumap, quic, ebpf, general) + metadata.py table including the pktmon pseudo-scenario
  parsing/
    wpa_exporter.py      ← xperf subprocess wrapper, all output parsers, export_all_profiles (parallel)
    csv_loader.py        ← BOM/comma-aware CSV → DataFrame normalization
    aggregator.py        ← parse_cpu_filter, apply_filters, group/sum, percentiles, time_bucket
  formatting/
    markdown.py          ← format_table, format_pct — every tool returns a markdown string
tests/                   ← pytest, synthetic data only — no xperf or .etl required
pyproject.toml           ← hatchling build, deps: mcp, pandas, pyarrow; dev: pytest

Read the full file on GitHub · 199 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 199 lines · 4,145 tokens per session scan A 6a9a17a82aff

Subscribe to this mod's changes

etw-mcp CLAUDE.md is an instructions file published in the GitHub repository nijosmsft/etw-mcp (12 stars, last pushed 1mo ago), licensed MIT. It adds 4,145 tokens to every session, about $0.0166 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Debugging etw mcp performance-analysis pktmon windows wpr

etw-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
etw-mcp CLAUDE.mdnijosmsft/etw-mcp	Instructions file	12	1mo ago	MIT	A	4,145	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

etw-mcp: Instructions file for Claude Code