golden-flow-mcp
Golden Flow Engine
用于构建、验证和运行项目专属 Golden Pack 的 Agent 中立引擎。它为 Codex、OpenClaw 及其他桌面 Agent 提供了确定性基础,用于理解仓库、设计自身的黄金流程、收集证据、恢复长时间运行,并随产品一起维护这些流程。
Engine 不是硬编码的 HTTP 测试运行器,也不调用任何 LLM。宿主 Agent 读取项目并写入 .golden-flow/;Engine 提供事实、安全工具、验证和执行。
快速开始
python -m pip install -e ".[mcp]"
golden-flow inspect /path/to/project
golden-flow init /path/to/project
golden-flow validate /path/to/project
golden-flow plan /path/to/project
golden-flow run /path/to/project --mode strict后台模式使用项目本地的 SQLite 队列:
golden-flow job-start /path/to/project
golden-flow worker /path/to/project --once
golden-flow job-status /path/to/project JOB_ID运行 golden-flow-mcp,通过 STDIO MCP 暴露检查、Pack 管理、规划和异步运行工具。固定的 Agent 工作流请参阅 AGENT_GUIDE.md。
Related MCP server: agent-orchestrator
内置适配器
file:限定在项目根目录内的读取、列表、哈希和存在性检查。shell:在policies/safety.yaml中显式注册的 argv 命令。http:使用 Python 标准库发送请求并收集响应证据。playwright:可选的浏览器导航、输入、截图和控制台错误。sql-observer:只读的 SQLite 观察;写入、pragma 和多语句会被拒绝。minium:可选的微信小程序能力,附带协议 Mock 模式以支持 CI。command-bridge:面向 TypeScript、Java、Go 和自定义工具的一个 JSON 进、一个 JSON 出的桥接器。
适配器协议使能力、预检、执行、证据、安全检查、错误分类和资源关闭均独立于 Engine 核心。
中文说明
golden-flow-engine 是给 Codex、OpenClaw/龙虾及其他桌面 Agent 使用的“项目黄金流程构建与运行引擎”。它先对仓库做确定性只读扫描,再由宿主 Agent 根据文档、代码、页面、状态模型和数据真相源,为该项目编写 .golden-flow/。Engine 负责目录格式、依赖拓扑、工具安全、证据完整性、前台/后台执行、断点结果和错误分类,不预置任何真实产品业务,也不内置模型 API。
默认提交项目画像、主干/分支清单、Python Journey、工具声明、策略和 Fixture 规则;默认忽略账号、Token、SQLite 运行状态、截图、日志、报告、缓存和真实业务资料。
状态
v0.1.0 是 alpha 版本。协议和 schema 名称已版本化,但 API 在 v1 之前仍可能演变。真正的 Minium 验收仍是在 Windows 上配合微信开发者工具进行的有文档说明的手动冒烟测试;常规 CI 使用协议 Mock。
采用 MIT 许可。请参阅 SECURITY.md 和 CONTRIBUTING.md。
This server cannot be installed
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
- FlicenseAqualityBmaintenanceGovernance/control plane for MCP-enabled coding-agent workflows with validation, findings, approvals, budgets, and proof bundles.5511
- AlicenseNot gradedqualityBmaintenanceEnables multi-model leader-worker agent orchestration, workflow execution, and deterministic validation via structured MCP tools.16Apache 2.0
- FlicenseNot gradedqualityCmaintenanceEnables MCP agents to inspect deployment knowledge extracted from a repository, covering workflows, services, deployments, and images.
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents and hosts to enforce deterministic repository boundaries via MCP, providing structured reads, supervised edits, snapshots, audits, and recovery with machine-readable evidence.MIT
Related MCP Connectors
Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.
Workflow diagnostics, capability routing, and x402 settlement for MCP-compatible agents.
Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST.
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/hkx5414375/golden-flow-engine'
If you have feedback or need assistance with the MCP directory API, please join our Discord server