My Pi coding agent setup: 17 plugins + 18 global skills + 2 MCP servers, with a one-line installer and tutorial README.
MCPpedia last refreshed this data
Pi Config is an MCP server that my Pi coding agent setup: 17 plugins + 18 global skills + 2 MCP servers, with a one-line installer and tutorial README. Its tool list has not been published yet over stdio and http, requires no API key, and scores 52/100 on MCPpedia's security, maintenance and efficiency rubric.
Config is the same across clients - only the file and path differ.
{
"mcpServers": {
"pi-config": {
"args": [
"-y",
"@earendil-works/pi-coding-agent"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
██████╗ ██╗ ██████╗ ██████╗ ███╗ ██╗███████╗██╗ ██████╗ ██╔══██╗██║ ██╔════╝██╔═══██╗████╗ ██║██╔════╝██║██╔════╝ ██████╔╝██║ ██║ ██║ ██║██╔██╗ ██║█████╗ ██║██║ ███╗ ██╔═══╝ ██║ ██║ ██║ ██║██║╚██╗██║██╔══╝ ██║██║ ██║ ██║ ██║ ╚██████╗╚██████╔╝██║ ╚████║██║ ██║╚██████╔╝ ╚═╝ ╚═╝ ╚═════╝ ╚═════╝ ╚═╝ ╚═══╝╚═╝ ╚═╝ ╚═════╝
Run this in your terminal to verify the server starts. Then let us know if it worked - your result helps other developers.
npx -y '@earendil-works/pi-coding-agent' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories - click any category to see the underlying evidence.
Pi Agent: Pi loads project-local extensions without approval
# Pi loads project-local extensions without approval Pi before 0.79.0 loaded project-local configuration and resources from a repository's `.pi` directory without first asking the user to trust that repository. This included project-local extensions, which are executable TypeScript or JavaScript modules loaded into the Pi process. An attacker who controls a repository could place Pi-specific project resources in that repository. If a user then started Pi from that working tree, the project-loc
Pi Agent: Predictable temporary extension install paths allow local privilege escalation on shared Linux hosts
# Predictable temporary extension install paths allow local privilege escalation on shared Linux hosts Pi versions with temporary npm or git extension package installs used predictable paths under the operating system temporary directory. On Linux-based multi-user systems, a local attacker who can write to the shared temporary directory could prepare the expected package location before another user runs pi with a temporary extension package source. Pi could then load attacker-controlled extens
Pi Agent: Race condition in Pi auth.json writes could expose stored credentials
# Pi auth.json writes could briefly expose stored credentials to local users Pi stored API keys and OAuth credentials in `auth.json`. A race condition in the file write path could briefly create or rewrite this file with permissions derived from the process umask before tightening the file to owner-only permissions. ## Info The affected credential storage code wrote `auth.json` and then corrected the file mode in a separate operation. During the interval between those operations, a local user
>= 0.28.0source →Pi Agent: Potential XSS in HTML session exports via Markdown URL sanitization bypass
# Potential XSS in HTML session exports via Markdown URL handling Pi HTML exports render session Markdown into a static HTML file. Affected versions did not consistently reject unsafe Markdown link and image URL schemes. In versions with scheme filtering, C0 control characters in the URL scheme could bypass the check because browsers normalize those characters before navigation. ## Impact The realistic attack path is indirect. An attacker would need to get suitable Markdown into a session, fo
>= 0.27.5source →Be the first to review
Have you used this server?
Share your experience - it helps other developers decide.
Sign in to write a review.
Others in education
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
2,700+ scientific tools for AI scientists: life science, research, literature, and more.
Daofy for Delphi — MCP Server that compiles Delphi projects and queries knowledge base for AI assistants.
Student-focused Canvas LMS: 237 tools for grades, deadlines, planning, submissions and study plans.
MCP Security Weekly
Get CVE alerts and security updates for Pi Config and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
██████╗ ██╗ ██████╗ ██████╗ ███╗ ██╗███████╗██╗ ██████╗
██╔══██╗██║ ██╔════╝██╔═══██╗████╗ ██║██╔════╝██║██╔════╝
██████╔╝██║ ██║ ██║ ██║██╔██╗ ██║█████╗ ██║██║ ███╗
██╔═══╝ ██║ ██║ ██║ ██║██║╚██╗██║██╔══╝ ██║██║ ██║
██║ ██║ ╚██████╗╚██████╔╝██║ ╚████║██║ ██║╚██████╔╝
╚═╝ ╚═╝ ╚═════╝ ╚═════╝ ╚═╝ ╚═══╝╚═╝ ╚═╝ ╚═════╝
17 plugins · 18 global skills · 2 MCP servers · one-line installer
一份可直接复刻的 Pi 配置,整理成教程形式分享。包含 17 个插件、18 个全局 Skill、2 个 MCP server,配一键安装脚本。
仓库里的每样东西都经过实际使用筛选,目标是把 Pi 打造成一个能多代理协作、能省 token、能跑浏览器的全能终端编码代理。
Pi(npm 包 @earendil-works/pi-coding-agent)是一个开源的终端 AI 编码代理。你给它一个任务,它在你本地的项目里读写文件、跑命令、调用工具来完成任务。
如果你还没装 Pi,先:
npm install -g @earendil-works/pi-coding-agent
然后跑 pi 进入交互界面。本仓库的所有插件都假设你已经有一个能正常工作的 Pi。
理解架构有助于你挑选和编写插件。Pi 是一个插件驱动的代理循环,核心分层:
┌─────────────────────────────────────────────────────┐
│ TUI / RPC / Print ← 用户交互层(终端界面 / API) │
├─────────────────────────────────────────────────────┤
│ Agent Loop ← 代理循环:收 prompt → 调模型 │
│ → 执行工具 → 回传结果 │
├─────────────────────────────────────────────────────┤
│ Providers / Models ← 多模型抽象:OpenAI / Anthropic │
│ / 本地 / 自定义 provider │
├─────────────────────────────────────────────────────┤
│ Tools ← 模型可调用的工具:bash/read/ │
│ edit/web_search/mcp/自定义 │
├─────────────────────────────────────────────────────┤
│ Extensions ← TypeScript 模块,能订阅事件、 │
│ 注册工具/命令/快捷键/主题 │
├─────────────────────────────────────────────────────┤
│ Skills / Prompts ← Markdown 形式的「过程知识」, │
│ 按需注入到模型上下文 │
├─────────────────────────────────────────────────────┤
│ Themes ← JSON 配色方案 │
├─────────────────────────────────────────────────────┤
│ Packages ← 上面这些资源的分发单位 │
│ (npm / git / 本地路径) │
└─────────────────────────────────────────────────────┘
关键概念:
tool_call 可以拦截/修改/阻止工具调用)、注册自定义工具、注册命令、改系统提示词、自定义渲染。SKILL.md 文件,描述「某类任务怎么做」。模型按需加载,跨会话存活。Pi 实现了 Agent Skills 标准,所以 Claude Code / OpenAI Codex 的 skill 也能直接用。.md 模板,用 /template 唤起。pi install 就是装包。代理循环的大致流程:
before_agent_start 事件(扩展可注入消息 / 改系统提示词)tool_call 事件(可拦截)→ 执行工具 → tool_result 事件(可改结果)→ 回传给模型agent_end → agent_settled扩展可以挂在任何一个环节上。
Pi 有一个官方的 包市场,所有在 package.json 里带 pi-package 关键字的 npm 包都会自动出现在上面。每个包页面会展示版本、下载量、依赖、仓库链接、甚至 demo 视频/截图。
在 Pi 里也可以直接搜包:
# 用 pi-marketplace 扩展(本仓库已装)
# 或命令行:
pi install npm:@s
... [View full README on GitHub](https://github.com/realchendahuang/pi-config#readme)