任务控制中心 是 AI Skill Hub 本期精选AI工具之一。已获得 4.8k 颗 GitHub Star,综合评分 8.5 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
任务控制中心 是一款基于 TypeScript 开发的开源工具,专注于 MCP工具、多智能体编排、AI自动化 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。
任务控制中心 是一款基于 TypeScript 开发的开源工具,专注于 MCP工具、多智能体编排、AI自动化 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。
# 方式一:npm 全局安装 npm install -g mission-control # 方式二:npx 直接运行(无需安装) npx mission-control --help # 方式三:项目依赖安装 npm install mission-control # 方式四:从源码运行 git clone https://github.com/builderz-labs/mission-control cd mission-control npm install npm start
# 命令行使用
mission-control --help
# 基本用法
mission-control [options] <input>
# Node.js 代码中使用
const mission_control = require('mission-control');
const result = await mission_control.run(options);
console.log(result);
# mission-control 配置说明 # 查看配置选项 mission-control --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 MISSION_CONTROL_CONFIG="/path/to/config.yml"
git clone https://github.com/builderz-labs/mission-control.git
cd mission-control
bash install.sh --local # or: bash install.sh --docker
After installation:
open http://localhost:3000/setup # create your admin account
The installer handles Node.js 22+, pnpm, dependencies, and auto-generates secure credentials. For Windows, use .\install.ps1 -Mode local in PowerShell.
git clone https://github.com/builderz-labs/mission-control.git
cd mission-control
nvm use 22 && pnpm install
pnpm dev # http://localhost:3000/setup
docker compose up # auto-generates credentials, persists across restarts
Register your first agent in under 5 minutes — no gateway required:
```bash export MC_URL=http://localhost:3000 export MC_API_KEY=your-api-key # shown in Settings after first login
1) Stand up a local control center in 5 minutes - Run bash install.sh --local - Open /setup - Create your first agent and task from the UI
2) Run multi-agent workflows with quality gates - Register specialist agents (research, coding, reviewer) - Enable orchestration rules and quality review - Track handoffs end-to-end in the Kanban board
3) Operate production safely - Deploy with docker-compose.hardened.yml - Configure MC_ALLOWED_HOSTS and TLS reverse proxy - Monitor trust score + security audit panels continuously
4) Integrate existing CLI agents without re-platforming - Connect Claude Code/Codex via CLI integration - Keep your current workflows while adding centralized observability and controls
---
Mission Control can run standalone without a gateway connection — useful for VPS deployments with firewall restrictions or when running primarily for project/task operations:
NEXT_PUBLIC_GATEWAY_OPTIONAL=true pnpm start
Task board, projects, agents, sessions, scheduler, webhooks, alerts, and cost tracking all work without a gateway. Real-time session updates and agent messaging require an active gateway connection.
See .env.example for the complete list. Key variables:
| Variable | Required | Description |
|---|---|---|
AUTH_USER | No | Initial admin username (default: admin) |
AUTH_PASS | No | Initial admin password (auto-generated if unset) |
API_KEY | No | API key for headless access (auto-generated if unset) |
OPENCLAW_CONFIG_PATH | No* | Absolute path to openclaw.json |
OPENCLAW_STATE_DIR | No* | Exact path to the OpenClaw state directory (default: ~/.openclaw). Preferred over OPENCLAW_HOME — avoids double-nesting |
OPENCLAW_HOME | No* | Legacy alias — treated as *parent* home dir (.openclaw is appended). Use OPENCLAW_STATE_DIR when it already points to the state dir |
MISSION_CONTROL_DATA_DIR | No | Directory for all MC data files (DB, tokens, etc.). Use an absolute path with the standalone server to survive rebuilds. |
MC_CLAUDE_HOME | No | Path to ~/.claude directory |
MC_ALLOWED_HOSTS | No | Host allowlist for production |
NEXT_PUBLIC_GATEWAY_OPTIONAL | No | Run without gateway connection |
*Required for memory browser, log viewer, and gateway features.
---
Mission Control exposes 101 REST endpoints documented via OpenAPI 3.1. Browse the interactive API docs at /api-docs (Scalar UI) when running locally, or see openapi.json.
<details> <summary><strong>Core endpoints at a glance</strong></summary>
| Area | Key Endpoints |
|---|---|
| **Agents** | GET/POST /api/agents, POST /api/agents/register, POST /api/agents/sync |
| **Tasks** | GET/POST /api/tasks, GET /api/tasks/queue, PUT /api/tasks/[id] |
| **Skills** | GET/POST /api/skills, GET/POST /api/skills/registry |
| **Security** | GET /api/security-audit, GET /api/security-scan |
| **Evals** | GET/POST /api/agents/evals, GET /api/agents/optimize |
| **Monitoring** | GET /api/status, GET /api/tokens, GET /api/activities |
| **Webhooks** | GET/POST/PUT/DELETE /api/webhooks, POST /api/webhooks/test |
| **Claude Code** | GET /api/claude/sessions, GET /api/claude-tasks |
| **Pipelines** | GET /api/pipelines, POST /api/pipelines/run |
| **Workspaces** | GET/POST /api/super/tenants, GET/POST /api/super/provision-jobs |
</details>
~/.claude/projects/, extracts token usage, model info, cost estimates, and active status.~/.claude/tasks/ and ~/.claude/teams/ on the dashboard.Outbound webhooks with delivery history, retry with exponential backoff, circuit breaker, and HMAC-SHA256 signature verification. GitHub Issues sync with label/assignee mapping. Agent inter-agent messaging via the comms API.
| Problem | Fix |
|---|---|
| "Internal server error" on login | pnpm rebuild better-sqlite3 (Node version mismatch) |
| Docker: gateway not connecting | Set OPENCLAW_GATEWAY_HOST=host.docker.internal in .env |
| Docker: browser WebSocket fails | Leave NEXT_PUBLIC_GATEWAY_HOST empty (auto-detected) or set to a browser-reachable hostname |
| 404 on all pages | Clear Next.js cache: rm -rf .next && pnpm dev |
AUTH_PASS with # ignored | Quote it: AUTH_PASS="my#pass" or use AUTH_PASS_B64 |
See docs/deployment.md for detailed troubleshooting.
Mission Control 是一个简介,描述了项目的基本信息。
Mission Control 的功能包括:
Mission Control 不需要任何环境依赖或系统要求。
Mission Control 支持多种安装方式,包括:
Mission Control 的使用教程包括:
Mission Control 的配置说明包括:
Mission Control 暴露了 101 个 REST 端点,通过 OpenAPI 3.1 文档化。
Mission Control 的工作流和模块包括:
Mission Control 的常见问题包括:
aiskill88点评:高质量MCP框架,Star数证明其受欢迎度。多智能体编排能力强,TypeScript实现便于扩展,活跃维护有保障。
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。
✅ 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。
经综合评估,任务控制中心 在AI工具赛道中表现稳健,质量优秀。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。
| 原始名称 | mission-control |
| 原始描述 | 开源MCP工具:Self-hosted AI agent orchestration platform: dispatch tasks, run multi-agent wor。⭐4.8k · TypeScript |
| Topics | MCP工具多智能体编排AI自动化任务分发Claude集成 |
| GitHub | https://github.com/builderz-labs/mission-control |
| License | MIT |
| 语言 | TypeScript |
收录时间:2026-05-14 · 更新时间:2026-05-16 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。