Orchestrator Python MCP Server
Orchestrator Python MCP Server
面向 AI 编码助手的机器验证式 4 阶段工作流 MCP 服务器。通过人工审批门禁、状态完整性检查和 DAG 任务调度,强制执行 DESIGN → PLAN → EXECUTE → VERIFY → COMPLETE 流程。
🚀 工作流生命周期
[Start] ──> orchestrate_init(task="...")
│
▼ (DESIGN Phase)
Write `.orchestrator/design.md`
│
▼
orchestrate_approve() ──> orchestrate_verify()
│
┌───────────────────────┘
▼ (PLAN Phase)
Write `.orchestrator/plan.md`
│
▼
orchestrate_approve() ──> orchestrate_verify()
│
┌───────────────────────┘
▼ (EXECUTE Phase)
orchestrate_get_dag_batches()
Subagents implement tasks & mark [x]
│
▼
orchestrate_verify()
│
▼ (VERIFY Phase)
orchestrate_verify() (runs automated test command)
│
▼ (COMPLETE Phase)
orchestrate_archive() ──> [Done]Related MCP server: Overture
🛠️ MCP 工具参考
工具名称 | 参数 | 描述 |
|
| 在 |
| (无) | 返回 |
| (无) | 人工门禁审批。解锁 |
| (无) | 验证阶段交付物。通过后推进到下一阶段,返回下一阶段的 SOP 提示。 |
| (无) | 解析 |
|
| 释放锁并将会话文件移动到 |
📋 各阶段交付物要求
DESIGN 阶段:
交付物:
.orchestrator/design.md必需标题:
## Requirements、## Architecture、## Self-Confidence Audit。门禁:验证前需调用
orchestrate_approve。
PLAN 阶段:
交付物:
.orchestrator/plan.md任务格式:
- [ ] **<id>**: <desc> (Agent: <role>, Target: <file>, blocked_by: [<deps>])详细规格:每个任务都需要一个
### <id>小节。最终关卡:最终任务必须指派给
Agent: implementation-reviewer,并被所有先前任务阻塞。测试命令:在
## Verification下提供有效的可执行Test command: <cmd>。门禁:验证前需调用
orchestrate_approve。
EXECUTE 阶段:
规则:
.orchestrator/plan.md中的所有任务必须标记为已勾- [x]。规则:目标文件必须存在于磁盘上,且大小大于 0 字节。
VERIFY 阶段:
规则:通过 shell 子进程运行计划中的测试命令(120 秒超时)。若退出码为 0,则通过。
⚡ 快速开始
安装与运行
# Sync environment
uv sync
# Run tests (Unit + 18 BDD Scenarios)
uv run pytest
# Start MCP server (stdio transport)
uv run python -m orchestrator_mcp.serverOpenCode MCP 配置(opencode.jsonconfig)
{
"mcpServers": {
"orchestrator": {
"command": "uv",
"args": ["run", "--directory", "/path/to/orchestrate", "python", "-m", "orchestrator_mcp.server"]
}
}
}Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI coding agents to execute formal, stateful workflows with typed contracts, postcondition enforcement, and structured retry logic.1Apache 2.0
- AlicenseNot gradedqualityBmaintenanceProvides interactive visual plans for AI coding agents, allowing users to review, approve, and monitor execution in real-time.8633MIT
- AlicenseNot gradedqualityAmaintenanceLocal-first AI agent for approval-gated automation and verifiable LLM workflows.1MIT
- AlicenseNot gradedqualityAmaintenanceEnables evidence-gated, multi-session AI coding runs with plan-build-ship state management, coordinating Claude Code and Codex native agents.41MIT
Related MCP Connectors
Adaptive plan/build/review cycles for AI coding assistants, persisted across sessions.
Runtime AI governance: decision gates, human approval, hash-chained audit, compliance mapping.
Human-in-the-loop for AI coding agents — ask questions, get approvals via Slack.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/eustin/mcp-server-orchestrate'
If you have feedback or need assistance with the MCP directory API, please join our Discord server