What it does
CLI framework and stdio MCP server for Flutter: scaffolding, hot reload, REPL, codegen.
- Connects –
- Account or key No key needed
- Category 开发者工具
可搭配使用
教 AI 做这类工作的 Skill,可与本项一起使用
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
为什么排在这里
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 6/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 0/8 | 上次检查时云端端点有响应 |
| 使用分 | 18/100 |
质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
安装
选择你使用的 AI 应用,然后复制设置。
通过 3/3 项检查 · 在你的电脑上运行
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
Claude 暂时无法连接 Dowel
开发者尚未在 MCP 注册表中填写安装方式
ChatGPT 暂时无法连接 Dowel
开发者尚未在 MCP 注册表中填写安装方式
你可以改用这些方式
B · 开发者工具 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的
- Sentry✓ ChatGPT
- Compiler Explorer✓ ChatGPT
- GitDiagram✓ ChatGPT
Claude Code 暂时无法连接 Dowel
开发者尚未在 MCP 注册表中填写安装方式
Cursor 暂时无法连接 Dowel
开发者尚未在 MCP 注册表中填写安装方式
VS Code 暂时无法连接 Dowel
开发者尚未在 MCP 注册表中填写安装方式
一览
它能做什么
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
基础检查i
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月19日
- ✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 anilcancakir 验证,该账户拥有此仓库
- ✓ 通过
仍在维护
代码最后更新于昨天
- ✓ 通过
有许可证
使用 MIT
- – 不适用
端点有响应
它在你的电脑上运行,没有互联网端点
- – 不适用
使用 OAuth 登录
在你的电脑上运行,改用本地设置
- … 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行;我们只能读取互联网端点的工具列表
作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/anilcancakir-dowel)讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
用户评价
还没有评价
与“开发者工具”中的其他服务器比较i
- 星标数多于此分类中其他 6103 个服务器的 77%
- 发布到注册中心的时间比此分类中其他 6103 个服务器的 99% 更新
- 基础检查结果等于或优于此分类中其他 6103 个服务器的 99%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
常见问题
Dowel 安全吗?
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
它需要哪些密钥或代码?
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在我的电脑上运行还是在云端?
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
它还在维护吗?
GitHub 仓库最后更新于昨天,最新版本(1.1.0)于昨天进入注册中心。
哪些应用可以使用它?
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。
有什么可以替代它?
同一分类中有:GitDiagram, Appllama, Cloudflare MCP, Omnara, Repowise
功能相近的其他选择
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
GitDiagram
Architecture diagrams, explanations and Mermaid source for public GitHub repositories.
Appllama
Study screens, flows and paywalls from top-earning iOS apps, then build from what wins.
Omnara
Deploy durable AI agents with Omnara, an open-source managed-agent platform.
Repowise
Codebase intelligence for AI coding agents: graph, git history, docs, decisions, code health.
| 本项 Dowel | GitDiagram | Appllama | Cloudflare MCP | Omnara | Repowise | |
|---|---|---|---|---|---|---|
| 运行位置 | 需要安装在电脑上 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 云端或安装在电脑上都可以 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 是 | 否 | 否 |
| 基础检查 | 3/3 | 4/4 | 4/4 | 4/4 | 4/4 | 5/5 |
| 许可证 | MIT | MIT | MIT | Apache-2.0 | Apache-2.0 | AGPL-3.0 |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Dowel
One binary for your Flutter dev loop and your AI agent.
Start, hot reload and inspect a running app, scaffold code, install plugins transactionally, and hand the same commands to your agent through a built-in MCP server.
Documentation · pub.dev · Issues
At a glance
| Fact | Value |
|---|---|
| Package | dowel |
| Install | dart pub add dowel, then dart run dowel install |
| Import | package:dowel/dowel.dart |
| Entry points | dart run dowel , ./bin/dowel, runDowel, DowelCommand, DowelServiceProvider, PluginInstaller, ./bin/dowel mcp:serve or dart run :dispatcher mcp:serve (substrate and plugin tools), dart run dowel:mcp (substrate tools only) |
| Platforms | macOS and Linux for the lifecycle commands (start, stop, reload, ...); the rest of the CLI and the MCP server run wherever Dart does |
| Requires | Dart >=3.13, Flutter for the app you drive |
| Dependencies | args, dart_mcp, vm_service, yaml_edit, xml, crypto, path, meta, stream_channel, yaml |
| License | MIT |
Install
dart pub add dowel
dart run dowel install
install writes bin/dispatcher.dart (the entry that calls runDowel), the codegen barrels lib/app/_plugins.g.dart and lib/app/commands/_index.g.dart, and builds the fast wrapper bin/dowel (about 0.2 s to start, against 0.4 to 2.7 s for dart run). Run it again and it skips every file that already exists (--force overwrites them) and keeps the dowel constraint your pubspec already has: install adds dowel: ^ only when the pubspec declares none. It adds only the machine-local cache to .gitignore (.dowel/cli-bundle*, .dowel/build.stamp* and .dowel/.dowel.lock/), so commit .dowel/plugins.json and .dowel/installed/.
Moving an app from fluttersdk_artisan? install stops on the files that package generated and prints what to delete and the commands to run; doctor warns about the same leftovers. The steps are in Migrating from fluttersdk_artisan.
dart run dowel list # every registered command, grouped by namespace
dart run dowel doctor # preflight: Flutter and Dart on PATH, the default port
Run the app under supervision
start launches flutter run detached and records the session per project under ~/.dowel/sessions/ /, so two apps can be driven at once and a command never acts on another project's app.
dart run dowel start --device=chrome
dart run dowel reload # hot reload, Dart state kept dart run dowel hot-restart # hot restart, Dart state dropped dart run dowel logs --follow dart run dowel stop
| Command | Effect |
|---|---|
start, stop, restart | Launch, tear down and relaunch the app; stop reaps the process group |
reload, hot-restart | Send r and R to the detached flutter run through a FIFO |
status, logs | Print the recorded session as JSON; print or follow the captured log |
tinker | A REPL (or --eval) that evaluates Dart in the running app over the VM Service |
A command that dials the running app (tinker among them) exits 75 while the app is still building, so a script can retry; any other non-zero code is a real failure.
Add a command
make:command Greet scaffolds the class and registers it in the nearest provider. The signature string declares the arguments and flags:
import 'package:dowel/dowel.dart';
final class GreetCommand extends DowelCommand { @override String get signature => 'greet {name} {--shout}';
@override String get description => 'Greet a person by name.';
@override CommandBoot get boot => CommandBoot.none;
@override Future handle(DowelContext context) async { final name = context.input.argument('name') ?? 'world'; final greeting = 'Hello, $name'; context.output.success( context.input.option('shout') == true ? greeting.toUpperCase() : greeting, ); return 0; } }
A command that the signature cannot express overrides configure(ArgParser) instead. Two providers registering the same command name fail at boot with DowelCommandCollisionException.
Install plugins
dart pub add awesome_plugin
dart run dowel plugin:install awesome_plugin --dry-run # preview every operation dart run dowel plugin:install awesome_plugin
A plugin describes its install footprint in an install.yaml manifest, or in code with the PluginInstaller DSL when it needs branching. Either way the installer stages every operation and writes nothing until the commit, writes through a .tmp file and a rename, skips what is already in place, and records each applied operation under .dowel/installed/ .json, so plugin:uninstall can reverse it. The reversal removes the files an install wrote, the dependencies it added and the plugin's registry entry; a dependency the project already declared stays, and edits injected into existing files (InjectImport, InjectAfterPattern) are logged as skipped, so remove those by hand. An install record written by an older dowel is refused until plugin:install --force rewrites it, and plugin:install refuses to run when lib/app/_plugins.g.dart registers providers but .dowel/plugins.json is missing: restore it from version control.
| Piece | Where it lives |
|---|---|
| Manifest: files to copy, provider and config wiring, Android, iOS, macOS and web edits, env vars, prompts | install.yaml in the plugin package |
Procedural escape hatch: writeFile, injectImport, injectProvider, injectAndroidPermission, injectEnvVar, ... | DowelInstallCommand subclass driving PluginInstaller |
| The plugin's commands | A DowelServiceProvider exported from package: /cli.dart |
A plugin without a manifest is registered directly in .dowel/plugins.json and needs the scaffold from dowel install. make:plugin generates a plugin package with all of this wired.
Give your agent the MCP server
./bin/dowel mcp:install # or: dart run dowel mcp:install
mcp:install writes the dowel entry into .mcp.json; reconnect your client once (Claude Code: /mcp reconnect dowel). The server speaks stdio JSON-RPC and exposes the substrate tools plus whatever the installed plugins contribute:
| Tool | Does |
|---|---|
dowel_start, dowel_stop, dowel_restart | Run the app lifecycle |
dowel_reload, dowel_hot_restart | Apply a code change to the running app |
dowel_status, dowel_logs, dowel_doctor, dowel_list | Read the session, the log (returned in the tool result), the toolchain and the command list |
dowel_tinker | Evaluate a Dart expression in the running app; a blank eval is a usage error |
dowel_start and dowel_restart take every option their CLI commands take. Without a running app the server stays up with the substrate tools and reconnects on the next call that needs the VM Service, after the app restarts too. A filter (.dowel/mcp.json, then DOWEL_MCP_* variables, then mcp:serve flags) allows or denies tools and packages; a deny wins at every layer.
Commands
| Namespace | Commands |
|---|---|
| Lifecycle | start, stop, status, logs, restart, reload, hot-restart |
| Scaffolding | install, make:plugin, make:command, make:fast-cli |
| Plugin management | plugin:install, plugin:uninstall, plugins:refresh |
| MCP | mcp:serve, mcp:install, mcp:uninstall |
| Introspection | help, list, doctor, tinker |
| Codegen | commands:refresh, test:bundle |
For AI coding agents
Rules for an agent working with this package. Each one is a mistake the maintainers already made once.
| Do | Because |
|---|---|
Run dart run dowel install once before plugin:install for a plugin without an install.yaml | The command registers into lib/app/_plugins.g.dart and stops without it |
Preview with plugin:install --dry-run before the real run | File writes swap in through .tmp files after staging, but dependency and injection edits write directly and are not rolled back (a failed install then reports rolledBack: false and leaves a partial record), and a conflict with a user-edited file needs a decision (a dry run returns before the conflict check, so it does not detect conflicts) |
Commit .dowel/plugins.json and .dowel/installed/; ignore only .dowel/cli-bundle*, .dowel/build.stamp* and .dowel/.dowel.lock/ | The registry regenerates lib/app/_plugins.g.dart; without it on a fresh clone plugin:install refuses to run |
Leave *.g.dart barrels alone; regenerate with commands:refresh and plugins:refresh | They are generated, a hand edit is overwritten |
Start the app with dowel start, not flutter run | Reload, restart, logs and tinker find the app through the recorded session |
In a git worktree, run dowel start there (or pass --state= ) before any command that uses the session (reload, stop, tinker, a plugin's :*) | The ownership check passes when the worktree sits inside the project root the main app recorded (an app at the repo root, the worktree under it) and for state with no recorded projectRoot; the command then acts on the main app and reports success. A sibling checkout, or an app in a subdirectory the worktree is not inside, is refused. MCP plugin tools and dowel_tinker run no such check. An MCP server resolves the session from its own working directory and falls back to the shared ~/.dowel/state.json pointer when that project has none, so it can reach the main app; run these from a shell inside the worktree. --state= skips the check, and a missing or unreadable file falls back to that pointer, so confirm the file exists and holds the intended projectRoot |
Reconnect the MCP client after mcp:install or a change to .dowel/mcp.json | Clients do not reload a server entry on their own |
Use ./bin/dowel mcp:serve (or dart run :dispatcher mcp:serve) for plugin tools | dart run dowel:mcp loads only the substrate tools |
Read the exit code: 75 means retry, anything else non-zero is a failure | The app may still be building |
Never treat bin/dowel.dart as a project wrapper | It is this package's own entry point; the wrapper is bin/dispatcher.dart |
Dependencies
dart_mcp for the MCP server, vm_service for the connection to the running app, args for command-line parsing, yaml and yaml_edit for manifests and in-place edits, xml for Android and Apple platform files, crypto for the install-record hashes. Dowel itself is pure Dart; the app you drive needs Flutter.
Links
- [Documentation](https://anilcancakir.com/