projectflow-dag-mcp
Provides a Gemini CLI extension for integrating with Google's Gemini AI agent.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@projectflow-dag-mcpload the tutorial project graph from examples/todo-tutorial.projectflow.json"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ProjectFlow DAG MCP 2.2.1
A local, model-independent DAG task coordinator for AI coding agents, with a static visual UI, validated state machine, resumable JSON progress, and MCP tools.
ProjectFlow 是一个面向 AI Agent 的本地 DAG 任务编排器。它把任务依赖、执行状态、验证证据和恢复操作保存在工程图 JSON 中,由 MCP Server 统一控制状态转换;网页 UI 负责查看和手工维护工程图。
它不替 Agent 写代码,也不绑定某个模型。任何支持 MCP tools 的 Agent 都可以使用同一套执行协议。

本项目不是 Google、Anthropic、OpenAI、GitHub 或其他 Agent 平台的官方产品,也与已有的同名 ProjectFlow 项目无隶属关系。
组成
projectflow-mcp/:状态机、并发锁、工程图校验和 Agent 执行协议。dist/projectflow-mcp.cjs:无需安装 npm 依赖的可分发 MCP bundle。index.html、app.js、index.css:工程图可视化界面。plugin.json、mcp_config.json、skills/:Antigravity 插件。gemini-extension.json、GEMINI.md、commands/:Gemini CLI Extension。adapters/:Codex、Claude、Copilot 和通用 Agent 的薄适配器。examples/todo-tutorial.projectflow.json:可直接跟随使用手册运行的完整教程图纸。
执行规则的唯一权威来源是 MCP tool get_execution_protocol。各平台 Skill/指令文件只负责触发它,避免多份流程逐渐不一致。
Related MCP server: dag-planner-mcp
构建与检查
需要 Node.js 20 或更高版本。
git clone https://github.com/wjmiracle/projectflow-dag-mcp.git
cd projectflow-dag-mcp
npm --prefix projectflow-mcp ci
npm run build
npm test
powershell -ExecutionPolicy Bypass -File .\scripts\install.ps1 -Action Validate安装
Antigravity CLI:
powershell -ExecutionPolicy Bypass -File .\scripts\install.ps1 -Client Antigravity -Action InstallGemini CLI:
powershell -ExecutionPolicy Bypass -File .\scripts\install.ps1 -Client Gemini -Action Install只更新独立 Skill,不安装完整插件:
powershell -ExecutionPolicy Bypass -File .\scripts\install.ps1 -Action Validate -InstallAntigravitySkill
powershell -ExecutionPolicy Bypass -File .\scripts\install.ps1 -Action Validate -InstallCodexSkillClaude、Copilot 和其他 MCP 客户端的配置样例见 adapters/README.md。
生成可上传到 GitHub Release、网盘或网站的精简发行包:
npm run pack输出位于 release/projectflow-dag-mcp-2.2.1.zip,同时生成 SHA-256 校验文件。用户解压后即可安装;发行包不包含 node_modules 和开发源码。
使用
在网页点击“生成步骤 JSON”,填写项目名称、产出目录和需求。
复制完整提示词并发送给任意 AI,把它返回的 JSON 保存到本地。
将 JSON 导入网页,并向执行 Agent 提供该文件的绝对路径。
Agent 加载服务器协议,原子领取任务,真实执行并验证,然后写回结果和证据。
UI 重新读取 JSON 后显示实时进度。
推荐通过本地 HTTP 打开 UI:
python -m http.server 8080然后访问 http://localhost:8080。
发布边界
只把静态网页放到公网,并不会让访问者自动获得 MCP 能力。完整发布应同时提供:
在线 UI,或可下载的静态 UI;
Antigravity/Gemini 插件包,或其他客户端的 MCP 配置;
bundle 后的
dist/projectflow-mcp.cjs;对应平台的薄 Skill/Agent 指令。
目前 MCP bundle 是本地 stdio 服务。若希望用户打开网页后无需本地安装,就还需要增加带认证和权限隔离的远程 HTTP MCP 服务。
详细格式、工具和排障说明见 使用手册.md。
文档与贡献
License
MIT © 2026 wjmiracle
This server cannot be deployed
Maintenance
Related MCP Connectors
Shared control plane for AI coding agents — tasks, memory, decisions, file locks. 12 tools.
- DazbenchOAuthapp.dazbench
Task management your AI agents can actually run. One line becomes a context-ready task over MCP.
AI work orchestration for plans, tasks, teams, and coding-agent dispatch.
Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.
Related MCP Servers
- FlicenseAqualityDmaintenanceA durable multi-agent orchestrator for software development with explicit run graphs, checkpoint/resume capabilities, and project memory exposed through MCP resources and tools. It enables coordinated agent workflows for coding, review, repair, CI, and approval with SQLite-backed memory retrieval and pluggable research backends.10-
- AlicenseBqualityDmaintenanceA durable DAG-based task planner exposed as an MCP server that lets AI orchestrators break a goal into a dependency graph of tasks, execute them in parallel where possible, track state durably, and handle human-in-the-loop approval through 22 MCP tools.24MIT
- AlicenseAqualityAmaintenanceLocal-first multi-agent delegation and approval control for Codex via MCP, with persistent task DAG, isolated worktrees, and a web console.141MIT
- AlicenseAqualityAmaintenanceMCP server that enables running and managing file-based AI Skills, Agents, and Flow workflows as DAGs, with tools for listing, executing, and resuming tasks via stdio JSON-RPC.9MIT