poirot — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by a7t-ai · MCP Server · ★ 216

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is poirot safe to install? View the security audit →

About poirot

POIROT Investigating your Claude Code sessions. A native macOS companion that lets you browse sessions, explore diffs, and re-run commands — all from a polished SwiftUI interface. Features &bull; Capabilities &bull; Getting Started &bull; Architecture &bull; Contributing &bull; Roadmap No login. No tracking. No analytics. No BYOK. No extra cost. Works offline. Less than 6 MB. <img src="https://img.youtube.com/vi/JLvNSRZrxd

aiclaudeclaude-codecodexcompanion-appdev-toolshomebrew-caskmacosmcpnative-macos

Quick Facts

Stars216
Forks14
LanguageSwift
CategoryMCP Server
LicenseMIT
Quality Score68.7302177662898/100
Open Issues5
Last Updated2026-08-28
Created2026-02-19
Platformsclaude-code, codex, mcp
Est. Tokens~18k

Compatible Skills

These tools work well together with poirot for enhanced workflows:

  • poirot — semantic(0.72)+complementary+rare_topics+same_lang+similar_pop+shared_platform (79%)
  • chops — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)
  • codex-island — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
  • workflow-audit — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
  • skills-manager — semantic(0.35)+complementary+same_lang+similar_pop+shared_platform (57%)

poirot alternative? Top 6 similar tools

Looking for a poirot alternative? If you're comparing poirot with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • TokenEater by AThevon · ⭐ 505

    Native macOS app to monitor AI usage limits and watch your coding sessions live

  • poirot by leonardocardoso · ⭐ 144

    A native macOS companion for Claude Code that lets you browse sessions, explore diffs, and re-run commands.

  • claude-code-apple-skills by rshankras · ⭐ 606

    Claude Code skills for Apple platform development (iOS, macOS, iPadOS) — product validation, code generation,

  • syrtis by Nanako0129 · ⭐ 400

    AI token usage & quota monitor for the macOS menu bar — native Swift, Liquid Glass, 3D contribution graph. Tra

  • cc-sessions-viewer by jerrywu001 · ⭐ 378

    support cc/codex/grok build/kimicode/pi/antigravity cli/opencode sessions viewer, skills manage, token usage s

  • TokenBar by Nanako0129 · ⭐ 367

    AI token usage & quota monitor for the macOS menu bar — native Swift, Liquid Glass, 3D contribution graph. Tra

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Swift Agent Tools

Frequently Asked Questions

What is poirot?

poirot is A native macOS companion for Claude Code that lets you browse sessions, explore diffs, and re-run commands.. It is categorized as a MCP Server with 216 GitHub stars.

What programming language is poirot written in?

poirot is primarily written in Swift. It covers topics such as ai, claude, claude-code.

How do I install or use poirot?

You can find installation instructions and usage details in the poirot GitHub repository at github.com/a7t-ai/poirot. The project has 216 stars and 14 forks, indicating an active community.

What license does poirot use?

poirot is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to poirot?

The top alternatives to poirot on Agent Skills Hub include TokenEater, poirot, claude-code-apple-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools