MCP 助手
- 作者仓库星标 0
- 作者仓库 skills-registry
When to use
Use this skill when the user wants to inspect or drive a running Flutter app from this conversation. Examples:
- "Tap the login button in my app"
- "Why is the home screen blank?"
- "Take a screenshot and tell me what's broken"
- "Expose my cart / flags / internal state to the agent via MCP"
If the user is asking about Flutter concepts unrelated to a running app (architecture questions, package selection), this skill does not apply.
Step 1: Preflight
Always run flutter-mcp-toolkit doctor --json first. Parse the output:
status: "ok"— proceed to Step 2.status: "error"anderror.code: "binary_not_found"— loadflutter-mcp-toolkit-setupand follow its install instructions.status: "error"anderror.code: "vm_not_connected"— loadflutter-mcp-toolkit-setupand follow its troubleshooting section.- Any other error — load
flutter-mcp-toolkit-debugand read the error envelope playbook.
Step 2: Pick the right skill for the user's intent
| User intent | Load skill |
|---|---|
| Read state ("what's on screen?", "show me errors", "screenshot") | flutter-mcp-toolkit-inspect |
| Drive UI ("tap X", "type into Y", "scroll to Z", "hot reload") | flutter-mcp-toolkit-control |
| Diagnose ("why is X failing?", "show recent logs", "evaluate expression") | flutter-mcp-toolkit-debug |
Register app-specific MCP tools/resources (MCPCallEntry, bootstrapFlutter additionalEntries) |
flutter-mcp-toolkit-custom-tools |
If the task spans more than one (e.g. "tap the button and show me what
changed"), load inspect AND control. Skills are additive.
Step 3: Execute
Each task skill has the tool list, parameter shapes, and example calls. Follow the prelude at the top of the skill — it tells you whether you're calling MCP tools or shelling out to the CLI.
Tool taxonomy reference
The core toolkit tools fall into these categories. The full list with parameter shapes lives in the task skills.
- Inspection (read-only):
discover_debug_apps,get_app_errors,get_screenshots,get_view_details,get_vm,get_extension_rpcs,semantic_snapshot,inspect_widget_at_point,capture_ui_snapshot,connect_debug_app. →flutter-mcp-toolkit-inspect. - Interaction (mutating):
tap_widget,long_press,enter_text,fill_form,scroll,swipe,drag,hover,press_key,wait_for,navigate,handle_dialog,hot_reload_flutter,hot_restart_flutter,hot_reload_and_capture. →flutter-mcp-toolkit-control. - Debug:
get_recent_logs,evaluate_dart_expression. →flutter-mcp-toolkit-debug. - Dynamic registry (app-defined): after registration in the Flutter app,
list with
list_client_tools_and_resources, thenclient_tool/client_resource— wire names asfmt_*when calling MCP. →flutter-mcp-toolkit-custom-tools.
When in doubt
If doctor is green but a tool call fails, read the returned error.code
and error.recovery fields. The full code → recovery table is in
flutter-mcp-toolkit-debug.
<!-- tomevault:4.0:skill_md:2026-05-22 -->Source: Arenukvern/mcp_flutter — distributed by TomeVault.
- 流狐分类
- AI 智能
- 作者声明 Agent
- 未找到明确声明;不据此推断已兼容或已测试
- 静态检查
- 88 / 100 · 启发式扫描,不代表运行安全
- 作者 / 版本 / 许可
- @tomevault-io · 未声明 license
- 流狐 Token 估算
- 低消耗
- 流狐接入估算
- 需简单配置
- 是否需要外部 API Key
- 未发现要求
- 检测到的系统要求
- 未声明
- 底层运行要求
- 未声明
- 检测到的文件与系统行为
-
- 只读
- Shell 执行
- 检测到的网络行为
- 仅限本地
- 安装命令数
- 无(仅作为资料)
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
作者没有在当前 SKILL.md 中定义固定输出样例。 Always run flutter-mcp-toolkit doctor --json first. Parse the output: status: "ok" — proceed to Step 2. status: "error" and error.code: "binarynotfound" — load
User intent · Load skill Read state ("what's on screen?", "show me errors", "screenshot") · flutter-mcp-toolkit-inspect Drive UI ("tap X", "type into Y", "scroll to Z", "hot reload") · flutter-mcp-toolkit-control
Each task skill has the tool list, parameter shapes, and example calls. Follow the prelude at the top of the skill — it tells you whether you're calling MCP tools or shelling out to the CLI.
<!-- @FMT_MODE_PRELUDE -->
## When to use
Use this skill when the user wants to inspect or drive a running Flutter app
from this conversation. Examples:
- "Tap the login button in my app"
- "Why is the home screen blank?"
- "Take a screenshot and tell me what's broken"
- "Expose my cart / flags / internal state to the agent via MCP"
If the user is asking about Flutter concepts unrelated to a running app
(architecture questions, package selection), this skill does not apply.
## Step 1: Preflight
Always run `flutter-mcp-toolkit doctor --json` first. Parse the output:
- `status: "ok"` — proceed to Step 2.
- `status: "error"` and `error.code: "binary_not_found"` — load
`flutter-mcp-toolkit-setup` and follow its install instructions.
- `status: "error"` and `error.code: "vm_not_connected"` — load
`flutter-mcp-toolkit-setup` and follow its troubleshooting section.
- Any other error — load `flutter-mcp-toolkit-debug` and read the error
envelope playbook.
## Step 2: Pick the right skill for the user's intent
| User intent | Load skill |
|---|---|
| Read state ("what's on screen?", "show me errors", "screenshot") | `flutter-mcp-toolkit-inspect` |
| Drive UI ("tap X", "type into Y", "scroll to Z", "hot reload") | `flutter-mcp-toolkit-control` |
| Diagnose ("why is X failing?", "show recent logs", "evaluate expression") | `flutter-mcp-toolkit-debug` |
| Register app-specific MCP tools/resources (`MCPCallEntry`, `bootstrapFlutter` `additionalEntries`) | `flutter-mcp-toolkit-custom-tools` |
If the task spans more than one (e.g. "tap the button and show me what
changed"), load `inspect` AND `control`. Skills are additive.
## Step 3: Execute
Each task skill has the tool list, parameter shapes, and example calls. Follow
… 作者原文负责流程事实;流狐只索引当前章节、要点、文件与命令。
章节 -> When to use → Step 1: Preflight → Step 2: Pick the right skill for the user's intent → Step 3: Execute → Tool taxonomy reference → When in doubt
要点 -> Inspection (read-only) · Interaction (mutating) · Debug · Dynamic registry (app-defined)
文件/命令 -> flutter-mcp-toolkit doctor --json · status: "ok" · status: "error" · error.code: "binarynotfound" · flutter-mcp-toolkit-setup · error.code: "vmnotconnected" · flutter-mcp-toolkit-debug · flutter-mcp-toolkit-inspect
内容 SHA-256 -> ae6f2fbca72a
方法与流程
适用与边界
原文中的明确线索
flutter-mcp-toolkit doctor --json、status: "ok"、status: "error"、error.code: "binarynotfound"、flutter-mcp-toolkit-setup、error.code: "vmnotconnected"、flutter-mcp-toolkit-debug、flutter-mcp-toolkit-inspect