What is mcp-hayabusa CLAUDE.md?

An MCP server that exposes Hayabusa, a Windows event-log forensics and timeline command-line tool, to an MCP client. It can scan .evtx files, the standard file format for Windows Event Logs.

Use it to scan EVTX files, list available detection rules, and expose those operations through the mcp-hayabusa server.

It removes the need to run the Hayabusa command-line tool manually when scanning event logs through an MCP client. Tests can also run without the real binary or sample logs.

How msadigo/mcp-hayabusa configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to msadigo/mcp-hayabusa. 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/msadigo/mcp-hayabusa/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/msadigo/mcp-hayabusa

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/msadigo/mcp-hayabusa/claude-md/github.svg)](https://agentmods.dev/instructions/msadigo/mcp-hayabusa/claude-md)

Your own site

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

Per session 2,304 This file is loaded in full into every session.

When invoked 2,304 The same file — it is already loaded in full.

Security scan A 1 finding. 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	$0.02304	$0.02304
Opus 5	$0.01152	$0.01152
Sonnet 5	$0.00461	$0.00461
Haiku 4.5	$0.00230	$0.00230

Measured 8d ago against content hash b57390690838, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-hayabusa CLAUDE.md scanned grade A with 1 finding 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 8d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

`sample_evtx/`. `scan()` tests monkeypatch `subprocess.run` with a fake that writes synthetic

CLAUDE.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

An MCP server that wraps the Hayabusa Windows event log forensics/timeline CLI tool, exposing it as an MCP tool (scan_evtx) so an MCP client can run Hayabusa detection scans over .evtx files.

Commands

pip install -e .          # install the package (and mcp[cli] dependency) in editable mode
mcp-hayabusa               # run the server over stdio (registered as a console script)
python -m mcp_hayabusa.server   # equivalent, without the console script

python scripts/download_hayabusa.py   # fetch the latest hayabusa binary for this platform into ./hayabusa/

pip install -e ".[test]"  # install with pytest
pytest                     # run the test suite

The test suite (tests/) is hermetic — it never invokes the real hayabusa binary or needs sample_evtx/. scan() tests monkeypatch subprocess.run with a fake that writes synthetic CSV/JSON to whatever -o path was requested; list_rules() tests run against a small synthetic rules directory (tests/conftest.py's rules_dir fixture); server.py tests monkeypatch hayabusa.scan/hayabusa.list_rules directly to test response-shaping in isolation. There is no linter or build step configured yet.

Manual testing

mcp dev (from the mcp[cli] package) launches the MCP Inspector against the server for interactive tool calls:

mcp dev src/mcp_hayabusa/server.py

Actually exercising scan_evtx requires the hayabusa binary to be installed (see Configuration below — scripts/download_hayabusa.py handles this) and at least one real or sample .evtx file. Yamato Security ships a repo of sample .evtx files that's useful for this — clone it into ./sample_evtx/ (gitignored, not a submodule):

git clone https://github.com/Yamato-Security/hayabusa-sample-evtx.git sample_evtx

Architecture

Two files carry all the logic:

Read the full file on GitHub · 149 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.

8d ago First seen · 149 lines · 2,304 tokens per session scan A b57390690838

Subscribe to this mod's changes

mcp-hayabusa CLAUDE.md is an instructions file published in the GitHub repository msadigo/mcp-hayabusa (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,304 tokens to every session, about $0.0115 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

mcp-hayabusa: Instructions file for Claude Code