能力标签
scarf MCP工具
🛠
AI工具

scarf MCP工具

基于 Swift · 开源 AI 工具,GitHub 社区精选
英文名:scarf
⭐ 502 Stars 🍴 31 Forks 💻 Swift 📄 MIT 🏷 AI 8.2分
8.2AI 综合评分
MCP工具AI代理macOS应用Swift开发多窗口管理
✦ AI Skill Hub 推荐

AI Skill Hub 强烈推荐:scarf MCP工具 是一款优质的AI工具。AI 综合评分 8.2 分,在同类工具中表现稳健。如果你正在寻找可靠的AI工具解决方案,这是一个值得深入了解的选择。

📚 深度解析
scarf MCP工具 是一款基于 Swift 的开源工具,在 GitHub 上收获 1k+ Star,是MCP工具、AI代理、macOS应用、Swift开发领域中的优质开源项目。开源工具的最大优势在于代码完全透明,你可以审计每一行代码的安全性,也可以根据自身需求进行二次开发和定制。

**为什么要使用开源工具而非商业 SaaS?**
对于个人开发者和有隐私需求的用户,本地部署的开源工具意味着数据不离本机,不受第三方服务商的数据政策约束。同时,开源工具通常没有使用次数限制和月度费用,一次安装即可长期使用,对于高频使用场景的总拥有成本(TCO)远低于订阅制商业工具。

**安装与环境准备**
scarf MCP工具 依赖 Swift 运行环境。建议通过 pyenv(Python)或 nvm(Node.js)管理 Swift 版本,避免全局环境污染。对于新手用户,推荐先创建虚拟环境(python -m venv venv && source venv/bin/activate),再安装依赖,这样即使出现问题也可以随时删除虚拟环境重新开始,不影响系统稳定性。

**社区与维护**
GitHub Issue 和 Discussion 是获取帮助的最快渠道。在提问前建议先检查 Closed Issues(已关闭的问题),大多数常见问题都已有解答。遇到 Bug 时,提供 pip list 的输出、完整错误堆栈和最小可复现示例,能显著提高开发者响应速度。AI Skill Hub 将持续追踪 scarf MCP工具 的版本更新,及时通知重要功能变化。
📋 工具概览

为Hermes AI智能体打造的原生macOS和iOS应用,支持多窗口、多服务器连接。提供图形化界面管理AI代理任务,适合需要桌面级AI工具体验的开发者和专业用户。

scarf MCP工具 是一款基于 Swift 开发的开源工具,专注于 MCP工具、AI代理、macOS应用 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。

GitHub Stars
⭐ 502
开发语言
Swift
支持平台
macOS / iOS
维护状态
正常维护,社区驱动
开源协议
MIT
AI 综合评分
8.2 分
工具类型
AI工具
Forks
31
📖 中文文档
以下内容由 AI Skill Hub 根据项目信息自动整理,如需查看完整原始文档请访问底部「原始来源」。

为Hermes AI智能体打造的原生macOS和iOS应用,支持多窗口、多服务器连接。提供图形化界面管理AI代理任务,适合需要桌面级AI工具体验的开发者和专业用户。

scarf MCP工具 是一款基于 Swift 开发的开源工具,专注于 MCP工具、AI代理、macOS应用 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。

📌 核心特色
  • 开源免费,支持本地部署,数据完全自主可控
  • 活跃的 GitHub 开源社区,持续迭代更新
  • 提供详细文档和使用示例,新手友好
  • 支持自定义配置,灵活适配不同使用环境
  • 可作为基础组件集成进现有技术栈或进行二次开发
🎯 主要使用场景
  • 本地部署运行,保护数据隐私,满足合规要求
  • 自定义集成到现有系统,扩展技术栈能力
  • 作为开源基础组件进行商业化二次开发
以下安装命令基于项目开发语言和类型自动生成,实际以官方 README 为准。
安装命令
# 克隆仓库
git clone https://github.com/awizemann/scarf
cd scarf

# 查看安装说明
cat README.md

# 按 README 完成环境依赖安装后即可使用
📋 安装步骤说明
  1. 访问 GitHub 仓库页面
  2. 按照 README 文档完成依赖安装
  3. 根据系统环境完成初始化配置
  4. 参考官方示例或文档开始使用
  5. 遇到问题可在 GitHub Issues 中查找解答
以下用法示例由 AI Skill Hub 整理,涵盖最常见的使用场景。
常用命令 / 代码示例
# 查看帮助
scarf --help

# 基本运行
scarf [options] <input>

# 详细使用说明请查阅文档
# https://github.com/awizemann/scarf
以下配置示例基于典型使用场景生成,具体参数请参照官方文档调整。
配置示例
# scarf 配置说明
# 查看配置选项
scarf --config-example > config.yml

# 常见配置项
# output_dir: ./output
# log_level: info
# workers: 4

# 环境变量(覆盖配置文件)
export SCARF_CONFIG="/path/to/config.yml"
📑 README 深度解析 真实文档 完整度 82/100 查看 GitHub 原文 →
以下内容由系统直接从 GitHub README 解析整理,保留代码块、表格与列表结构。

简介

<p align="center"> <img src="icon-v2.5.png" width="128" height="128" alt="Scarf app icon"> </p>

Scarf

<p align="center"> A native macOS companion app for the <a href="https://github.com/hermes-ai/hermes-agent">Hermes AI agent</a>.<br> Full visibility into what Hermes is doing, when, and what it creates. </p>

<p align="center"> <img src="https://img.shields.io/badge/macOS-14.6+%20Sonoma-blue" alt="macOS"> <img src="https://img.shields.io/badge/Swift-6-orange" alt="Swift"> <img src="https://img.shields.io/badge/license-MIT-green" alt="License"> <br> <em>Available in English, 简体中文, Deutsch, Français, Español, 日本語, and Português (Brasil).</em> <br><br> <a href="https://www.buymeacoffee.com/awizemann"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me a Coffee" height="28"></a> </p>

What's New in 2.9

A coordinated catch-up to Hermes v0.14.0 ("The Foundation Release"). v2.9 surfaces every Scarf-relevant feature from the v0.14 wave — the new /subgoal//yolo//sessions//codex-runtime slash commands, two new inference providers (xAI Grok OAuth + NovitaAI), two new gateway platforms (LINE + SimpleX Chat), two new web-search backends (Brave Search + DuckDuckGo), the OpenAI-compatible Hermes Proxy local server, ACP browser-tools setup, a YOLO mode warning banner, the Alibaba → Qwen Cloud display rename, and a stack of smaller settings/MCP/plugin additions. 24 new capability flags gate every surface; pre-v0.14 hosts render byte-identical to v2.8.0.

Features

Scarf mirrors Hermes's surface area through a sidebar-based UI. Sections below map 1:1 to the app's sidebar.

Remote setup requirements

The remote host must have:

  1. SSH access — key-based auth via your local ssh-agent. Scarf never prompts for passphrases; run ssh-add once in Terminal before connecting.
  2. sqlite3 on the remote $PATH — needed for the atomic DB snapshots. Install on the remote with apt install sqlite3 (Ubuntu/Debian), yum install sqlite (RHEL/Fedora), or apk add sqlite (Alpine).
  3. pgrep on the remote $PATH — used by the Dashboard "is Hermes running" check. Standard on every distro; install procps if missing.
  4. ~/.hermes/ readable by the SSH user. When Hermes runs as a separate user (systemd service, Docker container), the SSH user needs read access to config.yaml and state.db. Either (a) SSH as the Hermes user, (b) chmod Hermes's home to be group-readable and add your SSH user to that group, or (c) set the Hermes data directory field when adding the server to point at the right location (e.g. /var/lib/hermes/.hermes).

Requirements

  • macOS 14.6+ (Sonoma) for Scarf
  • iOS 18.0+ for ScarfGo (the iPhone companion, public TestFlight from v2.5)
  • Xcode 16.0+ to build from source
  • Hermes agent v0.6.0+ installed at ~/.hermes/ on each target host (v0.14.0+ recommended for full v2.9 feature support — /subgoal / /yolo / /sessions / /codex-runtime slash commands, xAI Grok OAuth + NovitaAI providers, LINE + SimpleX Chat platforms, Brave Search + DuckDuckGo web-search backends, MCP supports_parallel_tool_calls, Hermes Proxy local server, ACP --setup-browser, YOLO mode warning, Alibaba → Qwen Cloud display rename, docker_extra_args, display.timestamps, Cron deliver=all, Discord channel-history backfill, plugin tool_override badge, cross-session 1h Claude prefix cache. v0.13.0 still works for the v2.8 surface — Persistent Goals, ACP /queue, Kanban hallucination gate + diagnostics, Curator archive/prune, Google Chat, MCP SSE, etc.)
  • For remote servers: SSH access (key-based), sqlite3 on the remote (for atomic DB snapshots), and the hermes CLI resolvable from the remote user's PATH or at a path you specify per server. ScarfGo requires the same on every Hermes host it connects to.

Dependencies

PackagePurpose
[SwiftTerm](https://github.com/migueldeicaza/SwiftTerm)Terminal emulator for the Chat feature
[Sparkle](https://github.com/sparkle-project/Sparkle)Auto-updates from the GitHub-hosted appcast

Everything else uses system frameworks: SQLite3 C API, Foundation JSON, AttributedString markdown, SwiftUI Charts, GCD file watching.

ACP `--setup-browser` + YOLO warning

  • "Set up browser tools" button on the Health view header (v0.14+) runs hermes acp --setup-browser --assume-yes to install Chromium and provision Playwright in one shot. Inline status strip + 10-minute timeout (chromium download is slow).
  • YOLO mode warning — chat-header amber chip renders when approvals.mode = yolo and the host advertises hasYOLOWarning. Wired through ChatViewModel.approvalMode, refreshed off MainActor with the existing config diagnostics.

Install

Build from Source

git clone https://github.com/awizemann/scarf.git
cd scarf/scarf
open scarf.xcodeproj

Or from the command line:

xcodebuild -project scarf/scarf.xcodeproj -scheme scarf -configuration Release -arch arm64 -arch x86_64 ONLY_ACTIVE_ARCH=NO build

For an unsigned local Debug build without an Apple Developer account (handy for contributors), use ./scripts/local-build.sh — see BUILDING.md for prerequisites.

What You Can Build

  • Development dashboards — test coverage, build status, open issues, sprint progress
  • Data project trackers — pipeline metrics, data quality scores, processing throughput
  • Deployment monitors — deploy history tables, uptime stats, error rate charts
  • Research dashboards — experiment results, key findings, paper status checklists
  • Agent activity views — cron job results, content generation stats, task completion rates
  • Embedded web apps — local dev servers, HTML reports, Grafana dashboards, any web-based tool your agent generates
  • Any project status — if your agent can measure it, Scarf can display it

Quick Start

1. Create the dashboard file

Create .scarf/dashboard.json in any project folder:

{
  "version": 1,
  "title": "My Project",
  "description": "Project status at a glance",
  "sections": [
    {
      "title": "Overview",
      "columns": 3,
      "widgets": [
        {
          "type": "stat",
          "title": "Test Coverage",
          "value": "87%",
          "icon": "checkmark.shield",
          "color": "green",
          "subtitle": "+2.1% this week"
        },
        {
          "type": "progress",
          "title": "Sprint Progress",
          "value": 0.73,
          "label": "73% complete",
          "color": "blue"
        },
        {
          "type": "list",
          "title": "Tasks",
          "items": [
            { "text": "Write unit tests", "status": "done" },
            { "text": "Update API docs", "status": "active" },
            { "text": "Deploy to prod", "status": "pending" }
          ]
        }
      ]
    }
  ]
}

2. Register your project

In Scarf, go to Projects in the sidebar and click the + button to add your project folder. Or have your agent add it directly to the registry at ~/.hermes/scarf/projects.json:

{
  "projects": [
    { "name": "my-project", "path": "/Users/you/Developer/my-project" }
  ]
}

3. View in Scarf

Select your project in the Projects sidebar — the dashboard renders immediately. Scarf watches the file for changes and refreshes automatically whenever the JSON is updated.

`/subgoal` and three new chat-config slash commands

  • /subgoal <text> — layers extra success criteria onto an active /goal loop. Forms: <text> (add), remove N (drop the Nth), clear (empty the list). Optimistic local mirror on RichChatViewModel.activeSubgoals; the goal pill in the chat header gains a +N count badge with the full list in the hover tooltip.
  • /yolo — toggles dangerous-command auto-approval (approvals.mode = yolo) without leaving chat. Pairs with a new amber YOLO warning badge in the chat header so the state is always visible.
  • /sessions — browse and resume prior sessions inline.
  • /codex-runtime [auto|codex_app_server] — toggle the Codex app-server runtime for OpenAI/Codex models.
  • /handoff intentionally NOT in the ACP menu — verified against Hermes's command catalog: v0.14's /handoff <platform> is cli_only and hands a session to a messaging platform (Telegram/Discord/etc.), not to a different model. Mid-chat model switching keeps using the existing session/set_model RPC via the chat-header model badge.

MCP, settings, plugin additions

  • MCP supports_parallel_tool_calls — new optional flag on MCP server entries. Tri-state picker in the editor ("Default (Hermes decides)" / "Enabled" / "Disabled") writes supports_parallel_tool_calls: <bool> or drops the key entirely.
  • terminal.docker_extra_args — extra flags forwarded verbatim to docker run for the docker terminal backend. Comma-separated input; setter splits and serializes to YAML.
  • display.timestamps — per-message timestamp toggle for TUI output. (ACP-relayed chat in Scarf shows turn-duration chips independently, so this only affects the CLI.) Also fixed a pre-existing v0.13 oversight: display.language was in the model but the YAML parser wasn't reading it back at load.
  • Cron deliver=all — fan-out routing intent for cron jobs. Field placeholder + helper text updated on v0.14.
  • Discord channel-history backfill — default-on toggle for the v0.14 channel-history-read-on-join behavior; lets users opt out for noisy channels.
  • Plugin tool_override badge — plugins that declare tool_override: true in their manifest now render a visible badge in PluginsView so overridden built-in tools aren't a surprise.

Configure *(new in 1.6)*

  • Platforms — Native GUI setup for all 13 messaging platforms (Telegram, Discord, Slack, WhatsApp, Signal, Email, Matrix, Mattermost, Feishu, iMessage, Home Assistant, Webhook, CLI). Per-platform forms write credentials to ~/.hermes/.env and behavior toggles to ~/.hermes/config.yaml. WhatsApp and Signal pairing use an inline SwiftTerm terminal for QR scan and signal-cli daemon management
  • Personalities — List defined personalities, pick the active one, and edit SOUL.md inline with markdown preview
  • Quick Commands — Editor for custom /command_name shell shortcuts with dangerous-pattern detection (rm -rf, mkfs, etc.)
  • Credential Pools — Per-provider credential rotation with a fixed OAuth flow (URL extraction + browser open + code paste) and proper --type api-key handling. API keys never stored in UI state — only last-4 preview. Strategy picker (fill_first / round_robin / least_used / random)
  • Plugins — Install via Git URL or owner/repo, update, remove, enable/disable. Reads ~/.hermes/plugins/ directly for reliable state
  • Webhooks — Create, list, test-fire, and remove webhook subscriptions. Detects the "platform not enabled" state and links to gateway setup
  • Profiles — Switch between multiple isolated Hermes instances. Create, rename, delete, export (zip), import. Safe-switch warning reminds users to restart Scarf after activating a different profile
  • Hermes Proxy (new in 2.9, Hermes v0.14+) — Launch the OpenAI-compatible local proxy that forwards requests to your OAuth-authenticated upstream provider (Nous Portal in v0.14; more adapters as Hermes adds them). Status card with running/stopped badge, endpoint URL with copy button (http://127.0.0.1:8645/v1), provider picker, live log tail, and a usage-help card. Point Codex CLI / Aider / Cline / VS Code Continue at the endpoint and any bearer token works — the proxy attaches your real credential

Dashboard Schema Reference

{
  "version": 1,
  "title": "Required — dashboard title",
  "description": "Optional — subtitle text",
  "updatedAt": "Optional — ISO 8601 timestamp",
  "sections": [
    {
      "title": "Section Name",
      "columns": 3,
      "widgets": [{ "type": "...", "title": "..." }]
    }
  ]
}

Each section defines a grid with 1–4 columns. Widgets flow left-to-right, wrapping to new rows. See DASHBOARD_SCHEMA.md for the full schema reference with examples of every widget type.

Troubleshooting remote connections

If the connection pill is green but the Dashboard shows "Stopped", "unknown", or empty values, the SSH user can't read the Hermes state files. Open Manage Servers → 🩺 Run Diagnostics (or click the yellow "Can't read Hermes state" pill in the toolbar). The diagnostics sheet runs fourteen checks in one SSH session — connectivity, sqlite3 presence, read access to config.yaml and state.db, the effective non-login $PATH — and tells you exactly which one fails and why, with remediation hints for each. Use the Copy Full Report button to paste the full output into a bug report.

For the common "Hermes isn't at the default path" case (systemd services, Docker), Test Connection in the Add Server sheet now probes /var/lib/hermes/.hermes, /opt/hermes/.hermes, /home/hermes/.hermes, and /root/.hermes when it can't find state.db at ~/.hermes/, and offers a one-click fill if it finds any of them.

🎯 aiskill88 AI 点评 A 级 2026-05-20

高质量MCP工具实现,原生性能优异。多窗口架构设计合理,活跃维护,502星反映社区认可度良好。

📚 实用指南(长尾问题)
适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
  • 构建多智能体协作系统的 Agent 开发者
  • 做语音类 AI 产品的开发者
最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC,避免暴露公网
  • 生产部署优先使用 Docker Compose 隔离依赖,并挂载 volume 持久化数据
  • Agent 任务先做 dry-run 验证工具调用链,再开启自主执行
常见错误
  • API key 直接提交到 git 仓库(请用 .env 并加入 .gitignore)
  • MCP 配置路径拼错或权限不足,重启 Claude Desktop 才生效
  • 容器内无法访问宿主机 localhost — 使用 host.docker.internal
部署方案
  • Docker:scarf 提供官方镜像,docker compose up 一键启动
  • CLI:直接 npm install -g / pip install,命令行调用
  • 云端托管:可放在 Vercel / Railway / Fly.io 等 PaaS 平台
相关搜索
scarf 中文教程scarf 安装报错怎么办scarf MCP 配置scarf Docker 部署scarf Agent 工作流scarf 与同类工具对比scarf 最佳实践scarf 适合谁用
⚡ 核心功能
👥 适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
  • 构建多智能体协作系统的 Agent 开发者
  • 做语音类 AI 产品的开发者
⭐ 最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC,避免暴露公网
  • 生产部署优先使用 Docker Compose 隔离依赖,并挂载 volume 持久化数据
  • Agent 任务先做 dry-run 验证工具调用链,再开启自主执行
⚠️ 常见错误
  • API key 直接提交到 git 仓库(请用 .env 并加入 .gitignore)
  • MCP 配置路径拼错或权限不足,重启 Claude Desktop 才生效
  • 容器内无法访问宿主机 localhost — 使用 host.docker.internal
👥 适合人群
AI 技术爱好者研究人员和学生开发者和工程师技术创业者
🎯 使用场景
  • 本地部署运行,保护数据隐私,满足合规要求
  • 自定义集成到现有系统,扩展技术栈能力
  • 作为开源基础组件进行商业化二次开发
⚖️ 优点与不足
✅ 优点
  • +MIT 协议,可免费商用
  • +完全开源免费,无授权费用
  • +本地部署,数据完全自主可控
  • +开发者社区支持,遇问题可查可问
⚠️ 不足
  • 安装和初始配置可能需要一定技术基础
  • 功能完整性通常不如成熟商业产品
  • 技术支持主要依赖开源社区,响应速度不稳定
⚠️ 使用须知

AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。

建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。

📄 License 说明

✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。

🔗 相关工具推荐
📚 相关教程推荐
📰 相关 AI 新闻
🍿 AI 圈相关吃瓜
🗺️ 相关解决方案
🧩 你可能还需要
基于当前 Skill 的能力图谱,自动补全的工具组合
❓ 常见问题 FAQ
支持多服务器连接,兼容Hermes AI代理框架的各类后端服务。
💡 AI Skill Hub 点评

总体来看,scarf MCP工具 是一款质量优秀的AI工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。

📚 深入学习 scarf MCP工具
查看分步骤安装教程和完整使用指南,快速上手这款工具
🌐 原始信息
原始名称 scarf
原始描述 开源MCP工具:Native macOS and iOS App for the Hermes AI agent — multi-window, multi-server (l。⭐502 · Swift
Topics MCP工具AI代理macOS应用Swift开发多窗口管理
GitHub https://github.com/awizemann/scarf
License MIT
语言 Swift
🔗 原始来源
🐙 GitHub 仓库  https://github.com/awizemann/scarf 🌐 官方网站  https://awizemann.github.io/scarf/

收录时间:2026-05-16 · 更新时间:2026-05-19 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。