经 AI Skill Hub 精选评估,OpenSail — Claude MCP 必备工具中文教程 获评「强烈推荐」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.2 分,适合有一定技术背景的用户使用。
OpenSail — Claude MCP 必备工具中文教程 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
OpenSail — Claude MCP 必备工具中文教程 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/TesslateAI/OpenSail
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"opensail---claude-mcp---------": {
"command": "npx",
"args": ["-y", "opensail"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 OpenSail — Claude MCP 必备工具中文教程 执行以下任务... Claude: [自动调用 OpenSail — Claude MCP 必备工具中文教程 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"opensail___claude_mcp_________": {
"command": "npx",
"args": ["-y", "opensail"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <img src="assets/opensail-banner.png" alt="Tesslate OpenSail" width="100%" /> </p>
<p align="center"> OpenSail is the open-source alternative to Codex App, Claude Desktop, Cursor, and Cowork for agentic software work.<br /> <p align="center"> <a href="https://docs.tesslate.com"><strong>Docs</strong></a> · <a href="https://docs.tesslate.com/quickstart"><strong>Quickstart</strong></a> · <a href="https://discord.gg/DkzMzwBTaw"><strong>Join Discord</strong></a> · <a href="https://github.com/TesslateAI/opensail/releases"><strong>Releases</strong></a> </p>
<p align="center"> Build AI apps, agents, workflows, and automations you can inspect, run, share, and own.<br /> Turn recurring work from Slack, email, spreadsheets, tickets, approvals, and internal tools into runnable software.<br /> Manage your fleet of agents. Connect real systems. Add approvals, budgets, permissions, logs, schedules, and human review.<br /> Run it on your infrastructure. Use any model. Open source. Your cloud, your code, your control. </p>
<p align="center"> <a href="#"><img src="https://img.shields.io/badge/License-Apache_2.0-green?style=flat-square" alt="License" /></a> <a href="#"><img src="https://img.shields.io/badge/Platform-Linux_%7C_macOS_%7C_Windows-blue?style=flat-square" alt="Platform" /></a> <a href="#"><img src="https://img.shields.io/badge/Runtime-Kubernetes_Native-purple?style=flat-square" alt="Runtime" /></a> <a href="https://discord.gg/DkzMzwBTaw"><img src="https://img.shields.io/badge/Join_Discord-5865F2?style=flat-square&logo=discord&logoColor=white" alt="Join Discord" /></a> </p>
---
OpenSail is an open platform for building, running, and sharing AI workflows, apps, agents, and automations you can inspect and own.
It is for anyone with a process that keeps coming back: a founder chasing follow-ups, an operator buried in handoffs, a lawyer managing intake and documents, a support team routing issues, a developer building internal tools, or a company giving people a sanctioned place to build useful AI.
Start with a workflow in plain English: "every morning, check these sources, summarize what changed, update Linear, and send the result to Slack." OpenSail turns that into a real runnable system with a trigger, an agent or app action, selected tools and connectors, delivery targets, approval gates, budget limits, run history, and a sandboxed workspace when the workflow needs files, code, or services.
For builders, OpenSail is a way to turn useful AI experiments into durable software. For leaders, it is a control plane for letting teams move fast while keeping data, infrastructure, cost, permissions, and auditability under control.
Under the hood, OpenSail runs on portable, snapshot-backed workspaces. Agents and apps can sleep when idle, wake when needed, keep state across runs, and move from your local desktop to your own cloud with the same project state intact.
---
Describe the system you want, and let OpenSail draft the agent, automation, connectors, schedule, permissions, and review flow.
<p align="center"> <img src="assets/agent-builder.png" alt="Agent Builder authoring a new agent from chat" width="85%" /> </p>
OpenSail includes built-in agents that help people turn intent into reusable team assets.
Agent Builder: Mention @agent-builder, describe the agent you want, and it drafts a user-owned agent with a name, instructions, model preference, connected MCP servers, skills, and tool permissions. It uses the user's installed resources, produces a review card, and publishes after approval.
Automation Builder: Mention @automation-builder, choose one of your existing agents, describe the schedule and output target, and it drafts a user-owned automation. It attaches the cron trigger, prompt template, delivery targets, compute tier, and spend cap, then waits for the publish-and-activate review.
Service Integrator: Use the Service Integrator agent to connect services, configure MCPs and channels, and make sure agents have the tools they need before a workflow goes live.
These builders make the marketplace practical for everyday teams: build an agent, attach the right systems, schedule it, review it, and share it from the same chat surface.
<p align="center"> <img src="assets/agent-builder-details.png" alt="Agent Builder review card with the full agent configuration expanded" width="85%" /> </p>
---
Ship to 22 places by drawing an edge.
<p align="center"> <img src="assets/deployment-targets.png" alt="Pick from 22 deployment providers — serverless, container, static, and registry targets" width="85%" /> </p>
Deploy from the Architecture Panel. Draw an edge from a container to a deployment target. A/B deployments work naturally: connect the same container to two targets (Vercel for production, Cloudflare for preview) and each gets independent deployment history and rollback.
22 supported targets:
| Category | Targets |
|---|---|
| **Serverless / Full-stack** | Vercel, Netlify, Cloudflare Pages, DigitalOcean App Platform, Railway, Fly.io, Heroku, Render, Koyeb, Zeabur, Northflank |
| **Static hosting** | GitHub Pages, Surge, Deno Deploy, Firebase Hosting |
| **Container push** | AWS App Runner, GCP Cloud Run, Azure Container Apps, DigitalOcean Container Apps |
| **Registry / Export** | Docker Hub, GitHub Container Registry (GHCR), Download/Export (zip) |
Each target is a registry entry. Adding a new provider is one config block.
---
This is the most realistic first run for most people. It starts the frontend, backend, worker, gateway, Postgres, Redis, Traefik, and the devserver image used by user project containers.
Use Docker Desktop on macOS or Windows, Docker Engine on Linux, or Colima on macOS. On Windows, run the commands from WSL2 so bind mounts and project paths behave like Linux paths.
git clone https://github.com/TesslateAI/opensail.git
cd opensail
cp .env.example .env
Edit .env before first boot:
SECRET_KEY should be a real random value.LITELLM_API_BASE and LITELLM_MASTER_KEY are needed for agent/model calls. A working model proxy gives you the full agent experience.Then start the stack:
docker compose up --build -d
docker compose ps
Open http://localhost. API docs are at http://localhost:8000/docs.
The fuller Docker walkthrough is in docs/guides/docker-setup.md. After your first setup, the helper script is handy:
./scripts/docker.sh start
./scripts/docker.sh status
./scripts/docker.sh logs backend
If you are on macOS and want the repo to help install local tooling, use the interactive installer. It installs Homebrew dependencies, starts Colima, helps create .env, and lets you choose Docker Compose or Minikube.
git clone https://github.com/TesslateAI/opensail.git
cd opensail
./scripts/install-macos.sh
Use Docker Compose unless you specifically need Kubernetes behavior.
Rent your compute to other agents.
OpenSail exposes your running instance to the outside world through two interfaces:
Gateway API: External users (agents or humans) can interact with your OpenSail instance using an API key. They get their own sandboxed containers, can invoke agents, and run workflows. The API supports webhook callbacks on completion, scoped permissions per key, and project-level isolation.
MCP Server (in development): OpenSail itself becomes an MCP tool server. External coding agents (Claude Code, Cursor, Codex, or your own) can connect to your OpenSail instance, get sandboxed compute, use your agents, and publish apps directly from their development environment. Your instance becomes infrastructure that other agents can build on.
---
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。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
AI Skill Hub 点评:OpenSail — Claude MCP 必备工具中文教程 的核心功能完整,质量优秀。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | OpenSail |
| 原始描述 | OpenSail is the open-source alternative to Codex App, Claude Desktop, Cursor, and Cowork for agentic software work. |
| Topics | agentsaiautomationbtrfsconnectorsdeployment |
| GitHub | https://github.com/TesslateAI/OpenSail |
| License | Apache-2.0 |
| 语言 | Python |
收录时间:2026-05-22 · 更新时间:2026-05-22 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端