pi-harness — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

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 wangmiaozero · MCP Server · ★ 83

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

🔒 Is pi-harness safe to install? View the security audit →

About pi-harness

Pi-Harness English · 简体中文 · 繁體中文 · 日本語 · 한국어 · Русский · Français · Deutsch Desktop Harness &amp; Control Center for Pi Coding Agent Bring Pi Agent Harness into a visual desktop workspace. Everything around Pi, in one place. Manage models · Run agents · Orchestrate teams · Inspect Harness state · Use Skills · Browse files · Control Git Download Pi-Harness · Pi Agent Harness · Screenshots <img alt="license AGPL-3.0-only" src="https://img.shields.io/badge/license-AGPL--3.0--only-

agent-consoleagent-harnessagent-runtimeai-agentai-codingcoding-agentcoding-assistantdesktop-appdeveloper-toolselectron

Quick Facts

Stars83
Forks7
LanguageTypeScript
CategoryMCP Server
LicenseAGPL-3.0
Quality Score64.0275567357865/100
Last Updated2026-09-20
Created2026-08-20
Platformsmcp, node
Est. Tokens~19k

Compatible Skills

These tools work well together with pi-harness for enhanced workflows:

  • pi-desktop — semantic(0.71)+complementary+same_lang+similar_pop+shared_platform (75%)
  • percho — semantic(0.70)+complementary+same_lang+similar_pop+shared_platform (74%)

pi-harness alternative? Top 6 similar tools

Looking for a pi-harness alternative? If you're comparing pi-harness 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.

  • runjam by peintune · ⭐ 181

    One desktop for all your AI coding Agent — Claude Code, Codex CLI & Gemini CLI. Auto-detect, one-click install

  • pi by TGYD-helige · ⭐ 66

    Pluggable extension packages for the Pi AI-agent runtime. Each package exposes LLM-callable tools via MCP — co

  • pi-tool-display by MasuRii · ⭐ 250

    Compact tool call rendering, diff visualization, and output truncation extension for Pi coding agent. Hides, c

  • palot by ItsWendell · ⭐ 187

    Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes

  • claude-code-open by kill136 · ⭐ 158

    Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.

  • bitrouter by bitrouter · ⭐ 228

    The context-aware model router that learns & adapts to your long-horizon coding agent workflows. Lightweight &

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is pi-harness?

pi-harness is Visual desktop Harness & control center for Pi Coding Agent — inspect runtime, context, tools & sessions; manage models & skills; browse files & Git. Powered by Pi Agent Harness.. It is categorized as a MCP Server with 83 GitHub stars.

What programming language is pi-harness written in?

pi-harness is primarily written in TypeScript. It covers topics such as agent-console, agent-harness, agent-runtime.

How do I install or use pi-harness?

You can find installation instructions and usage details in the pi-harness GitHub repository at github.com/wangmiaozero/pi-harness. The project has 83 stars and 7 forks, indicating an active community.

What license does pi-harness use?

pi-harness is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to pi-harness?

The top alternatives to pi-harness on Agent Skills Hub include runjam, pi, pi-tool-display. 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