agent-fleet-o MCP工具 是 AI Skill Hub 本期精选MCP工具之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
本连为服务给的常用的模式,当前为常用的常用的模式。
agent-fleet-o MCP工具 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。
本连为服务给的常用的模式,当前为常用的常用的模式。
agent-fleet-o MCP工具 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/escapeboy/agent-fleet-o
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"agent-fleet-o-mcp--": {
"command": "npx",
"args": ["-y", "agent-fleet-o"]
}
}
}
# 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 agent-fleet-o MCP工具 执行以下任务... Claude: [自动调用 agent-fleet-o MCP工具 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": {
"agent-fleet-o_mcp__": {
"command": "npx",
"args": ["-y", "agent-fleet-o"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Self-hosted mission control for AI agents. Build, run, and monitor autonomous multi-agent systems with a visual DAG builder, human-in-the-loop approvals, MCP server integration, and full audit trail. Works with Claude, GPT-4o, Gemini, Ollama, Codex, Claude Code, and any OpenAI-compatible LLM.
Keywords: AI agents · agent orchestration · MCP server · Model Context Protocol · LangGraph alternative · CrewAI alternative · n8n for AI · Claude agents · LLM workflow · autonomous agents · agent framework · AI automation · self-hosted
☁️ Prefer managed? Try FleetQ Cloud — zero setup, free tier. ⭐ Like the project? Give it a star on GitHub — it helps others find FleetQ.
---
ANTHROPIC_API_KEY= OPENAI_API_KEY= GOOGLE_AI_API_KEY=
git clone https://github.com/escapeboy/agent-fleet-o.git
cd agent-fleet
make install
This will: 1. Copy .env.example to .env 2. Build and start all Docker services 3. Run the interactive setup wizard (database, admin account, LLM provider)
Visit http://localhost:8080 when complete.
Requirements: PHP 8.4+, PostgreSQL 17+, Redis 7+, Node.js 20+, Composer
```bash git clone https://github.com/escapeboy/agent-fleet-o.git cd agent-fleet composer install npm install && npm run build cp .env.example .env
If you're running FleetQ locally on your own machine and don't want to enter a password on every visit, set APP_AUTH_BYPASS=true in .env:
APP_AUTH_BYPASS=true # Auto-login as first user
APP_ENV=local # Required — bypass is disabled in production
With bypass enabled, the app logs you in automatically on every request. A logout link is still shown but you'll be logged back in on the next page load — this is intentional.
Warning: Never set APP_AUTH_BYPASS=true on a server accessible from the internet.
The containers reach the host machine via host.docker.internal, which is pre-configured in docker-compose.yml via extra_hosts: host.docker.internal:host-gateway.
Step 1 — Enable SSH on the host
| OS | Command |
|---|---|
| macOS | System Settings → General → Sharing → **Remote Login** → On |
| Ubuntu/Debian | sudo apt install openssh-server && sudo systemctl enable --now ssh |
| Fedora/RHEL | sudo dnf install openssh-server && sudo systemctl enable --now sshd |
| Windows | Settings → System → Optional Features → **OpenSSH Server**, then Start-Service sshd |
Step 2 — Generate an SSH key pair
ssh-keygen -t ed25519 -C "fleetq-agent@local" -f ~/.ssh/fleetq_agent_key -N ""
Step 3 — Authorize the key on the host
cat ~/.ssh/fleetq_agent_key.pub >> ~/.ssh/authorized_keys
chmod 600 ~/.ssh/authorized_keys
Step 4 — Create a Credential in FleetQ
Navigate to Credentials → New Credential: - Type: SSH Key - Paste the contents of ~/.ssh/fleetq_agent_key (private key)
Or via API:
curl -X POST http://localhost:8080/api/v1/credentials \
-H "Authorization: Bearer $TOKEN" \
-H "Content-Type: application/json" \
-d '{
"name": "Host SSH Key",
"credential_type": "ssh_key",
"secret_data": {"private_key": "<contents of fleetq_agent_key>"}
}'
Step 5 — Create an SSH Tool
Navigate to Tools → New Tool → Built-in → SSH Remote, or via API:
curl -X POST http://localhost:8080/api/v1/tools \
-H "Authorization: Bearer $TOKEN" \
-H "Content-Type: application/json" \
-d '{
"name": "Host SSH",
"type": "built_in",
"risk_level": "destructive",
"transport_config": {
"kind": "ssh",
"host": "host.docker.internal",
"port": 22,
"username": "your-username",
"credential_id": "<credential-id>",
"allowed_commands": ["ls", "pwd", "whoami", "uname", "date", "df"]
},
"settings": {"timeout": 30}
}'
Step 6 — Assign the tool to an agent
In the Agent detail page, go to Tools and assign the SSH tool. The agent will now have an ssh_execute function available during execution.
| Service | Purpose | Port |
|---|---|---|
| app | PHP 8.4-fpm | -- |
| nginx | Web server | 8080 |
| postgres | PostgreSQL 17 | 5432 |
| redis | Cache/Queue/Sessions | 6379 |
| horizon | Queue workers | -- |
| scheduler | Cron jobs | -- |
| vite | Frontend dev server | 5173 |
FleetQ is built for teams running AI agents in production, not toy demos.
gpu_compute skill on RunPod serverless (Whisper, FLUX, Bark) as part of a larger workflow, with cost accounting.|
Dashboard KPI overview with active experiments, success rate, budget spend, and pending approvals. <img src="screenshots/qa-dashboard.png" width="100%" alt="Dashboard"> </td> <td width="50%"> Agent Template Gallery Browse 14 pre-built agent templates across 5 categories. Search, filter by category, and deploy with one click. <img src="screenshots/qa-agent-templates.png" width="100%" alt="Agent Templates"> </td> </tr> <tr> <td> Agent LLM Configuration Per-agent provider and model selection with fallback chains. Supports Anthropic, OpenAI, Google, and local agents. <img src="screenshots/agent-llm-edit-panel.png" width="100%" alt="Agent LLM Config"> </td> <td> Agent Evolution AI-driven agent self-improvement. Analyze execution history, propose personality and config changes, and apply with one click. <img src="screenshots/qa-evolution-tab.png" width="100%" alt="Agent Evolution"> </td> </tr> <tr> <td> Crew Execution Live progress tracking during multi-agent crew execution. Each task shows its assigned skill, provider, and elapsed time. <img src="screenshots/tasks-panel-building.png" width="100%" alt="Crew Execution"> </td> <td> Task Output Expand any completed task to inspect the AI-generated output, including structured JSON responses. <img src="screenshots/tasks-expanded-output.png" width="100%" alt="Task Output"> </td> </tr> <tr> <td> Visual Workflow Builder DAG-based workflow editor with conditional branching, human tasks, switch nodes, and dynamic forks. <img src="screenshots/qa-workflows.png" width="100%" alt="Workflows"> </td> <td> Tool Management Manage MCP servers, built-in tools, and external integrations with risk classification and per-agent assignment. <img src="screenshots/qa-tools.png" width="100%" alt="Tools"> </td> </tr> <tr> <td> AI Assistant Sidebar Context-aware AI chat embedded in every page with 28 built-in tools for querying and managing the platform. <img src="screenshots/assistant-sidebar.png" width="100%" alt="Assistant Sidebar"> </td> <td> Experiment Detail Full experiment lifecycle view with timeline, tasks, transitions, artifacts, metrics, and outbound delivery. <img src="screenshots/qa-experiment-detail.png" width="100%" alt="Experiment Detail"> </td> </tr> <tr> <td> Settings & Webhooks Global platform settings, AI provider keys (BYOK), outbound connectors, and webhook configuration. <img src="screenshots/settings-page-full.png" width="100%" alt="Settings"> </td> <td> Error Handling Failed tasks display detailed error information including provider, error type, and request IDs for debugging. <img src="screenshots/tasks-panel-error-expanded.png" width="100%" alt="Error Handling"> </td> </tr> </table> Edit .env — set DB_HOST, DB_DATABASE, DB_USERNAME, DB_PASSWORD, REDIS_HOSTphp artisan key:generate php artisan migrate php artisan horizon & php artisan serve ``` Then open http://localhost:8000 in your browser. The setup page will guide you through creating your admin account. Alternative: Run
ConfigurationAll configuration is in ```bash API & MCP surface
Agents, crews, and workflows
Integrations & web dev pipeline
How FleetQ compares
TL;DR — if you're building production agent systems with LLMs and want visual workflows + MCP + human oversight, FleetQ is the only platform that bundles all of it.
🇨🇳 中文文档镜像
AI 翻译
2026-05-23
英文原文章节由系统翻译为中文摘要,便于快速理解。完整原文见上方 "📑 README 深度解析"。
📌 简介
FleetQ 是一个开源的 AI 代理调度平台,提供自主部署的任务控制功能。它支持可视化的 DAG 构建器、人机交互的批准流程、MCP 服务器集成和全面的审计记录。FleetQ 支持 Claude、GPT-4o、Gemini、Ollama、Codex、Claude Code 和任何兼容 OpenAI LLM 的 AI 代理。 ⚡ 功能介绍
FleetQ 提供了以下功能: 📋 环境依赖
环境依赖与系统要求: 🚀 使用教程
FleetQ 的使用场景包括: 🔌 API 说明
API/接口说明: 🔄 工作流/模块
工作流 / 模块说明:
🎯 aiskill88 AI 点评
A 级
2026-05-23
本连为服务给的常用的模式、常用的常用的模式。当前为常用的常用的模式。 📚 实用指南(长尾问题)
适合谁
最佳实践
常见错误
部署方案
⚡ 核心功能
👥 适合谁
⭐ 最佳实践
⚠️ 常见错误
👥 适合人群
🎯 使用场景
⚖️ 优点与不足
✅ 优点
⚠️ 不足
⚠️ 使用须知
该工具使用 AGPL-3.0 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。 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
⚠️ AGPL 3.0 — 最严格的 Copyleft,网络服务端使用也需开源,SaaS 使用受限。 📚 相关教程推荐 📰 相关 AI 新闻
🍿 AI 圈相关吃瓜
🧩 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
请给编号。
💡 AI Skill Hub 点评
经综合评估,agent-fleet-o MCP工具 在MCP工具赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。 🌐 原始信息
🔗 原始来源
🐙 GitHub 仓库 https://github.com/escapeboy/agent-fleet-o
🌐 官方网站 https://fleetq.net
收录时间:2026-05-17 · 更新时间:2026-05-19 · License:AGPL-3.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。 🤖 交给 Agent 安装 · agent-fleet-o MCP工具选择 Agent 类型,复制安装指令后粘贴到对应客户端 claude skill install https://github.com/escapeboy/agent-fleet-o
|