configure-canvas-mcp

作者: microsoft

為 Claude Code、VS Code Copilot 或 GitHub Copilot CLI 設定 Canvas Authoring MCP 伺服器。當出現「設定 MCP」、「設定 MCP 伺服器」、「MCP 未…」時使用。

npx skills add https://github.com/microsoft/power-platform-skills --skill configure-canvas-mcp

Configure the Canvas Authoring MCP Server

This skill configures the Canvas Authoring MCP server for the user's current Power Apps coauthoring session. The MCP server is auto-registered by the plugin — this skill connects it to a specific app session.

Instructions

1. Ask for the studio URL

Ask the user:

What is the URL of your canvas app studio session?

Copy the URL from the browser address bar while your app is open in Power Apps Designer (it should look like https://make.powerapps.com/e/Default-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/canvas/?action=edit&app-id=...).

Make sure coauthoring is enabled in the app (Settings → Updates → Coauthoring).

Keep this browser tab open for the entire session. The MCP server communicates with Power Apps through the coauthoring session tied to that tab. Closing the tab ends the coauthoring session, which prevents compile_canvas and sync_canvas from working and means you can't see or save generated changes.

2. Extract parameters from the URL

Parse the following from the studio URL:

  • ENV_ID: the path segment between /e/ and the next / (e.g. Default-91bee3d9-0c15-4f17-8624-c92bb8b36ead).
  • APP_ID: URL-decode the app-id query parameter value, then take the last segment after the final / (e.g. 6fc3e3d1-292b-4281-8826-577f78512e56)
  • MAKER_HOSTNAME: the hostname of the URL (e.g. make.powerapps.com)
  • ENVIRONMENT_CATEGORY: determined from MAKER_HOSTNAME (see table below)

Determine ENVIRONMENT_CATEGORY from MAKER_HOSTNAME:

MAKER_HOSTNAMEENVIRONMENT_CATEGORY
make.powerapps.comprod
make.preview.powerapps.comprod
make.preprod.powerapps.compreprod
make.gov.powerapps.usgov
make.high.powerapps.ushigh
make.apps.appsplatform.usdod
make.powerapps.cnchina
Any other hostnametest

Example:

Example URL: https://make.powerapps.com/e/Default-91bee3d9-0c15-4f17-8624-c92bb8b36ead/canvas/?action=edit&app-id=%2Fproviders%2FMicrosoft.PowerApps%2Fapps%2F6fc3e3d1-292b-4281-8826-577f78512e56

  • ENV_ID → Default-91bee3d9-0c15-4f17-8624-c92bb8b36ead
  • APP_ID → 6fc3e3d1-292b-4281-8826-577f78512e56
  • MAKER_HOSTNAME → make.powerapps.com
  • ENVIRONMENT_CATEGORY → prod

3. Configure the MCP server

Call the connect MCP tool to connect the server to the user's coauthoring session:

mcp__canvas-authoring__connect(
  environment_id: ENV_ID,
  app_id: APP_ID,
  environment_category: ENVIRONMENT_CATEGORY,
  // Optional — include only if the user has expressed a preference or a prior sign-in failed (see below):
  auth_flow: "broker" | "browser" | "devicecode",
  login_hint: "user@contoso.com",
  tenant_id: "00000000-0000-0000-0000-000000000000",
  force_account_select: true
)

Optional parameters — do NOT prompt the user for these. Only include them if the user has already expressed a preference earlier in the conversation, or if a prior connect attempt failed:

  • login_hint: Pass the user's UPN or email only if they have indicated they want to connect as a specific/different user (e.g. "log in as alice@contoso.com"). These values cannot be derived from the maker portal URL — never guess. Omit otherwise to use the first signed-in user. When reconnecting to switch environment/app, reuse the same login_hint value as the previous successful connect (if known) so the same user is reused without re-prompting.
  • auth_flow: Pass "browser", "broker", or "devicecode" only if the user has explicitly stated a preferred auth flow (e.g. "use browser sign-in"). Use "devicecode" on headless/SSH hosts where neither broker nor browser flow can pop a UI — the verification URL and user code are surfaced via an MCP elicitation request and require a client that supports elicitation. Omit otherwise to use the default.
  • tenant_id: Pass a tenant GUID only for Entra B2B guest access — set it to the host/resource tenant where the user is a guest so the token is issued by that tenant rather than the user's home tenant. Combine with login_hint (the guest's home UPN) to pre-fill the account. Omit for normal same-tenant sign-in.
  • force_account_select: Pass true only to force the account picker instead of silently reusing a cached account — set this when a previous connect failed with a 401/403 and no login_hint was given, so the user can pick the correct account. Omit otherwise.

If the mcp__canvas-authoring__connect tool is not available (the MCP server did not start), run the following command to check whether the server failed to launch due to a missing .NET 10 SDK:

dotnet --list-sdks

If a version 10.x.y or higher is not listed, tell the user:

⚠️ .NET 10 SDK is required to run the Canvas Authoring MCP server. It looks like you don't have it installed. Please install it from https://dotnet.microsoft.com/download/dotnet/10.0 and then try again.

If the tool is available but the call returns an error, report the error and suggest checking that:

  1. The studio URL is correct and the browser tab is still open
  2. Coauthoring is enabled in the app settings
  3. If sign-in failed, the user may need to specify auth_flow (broker, browser, or devicecode) or a login_hint (UPN/email) to authenticate as the correct account. On a headless/SSH host, use auth_flow: "devicecode". If a cached account keeps getting picked, retry with force_account_select: true. For Entra B2B guest access, set tenant_id to the host tenant.

4. Confirm

Tell the user:

✅ Canvas Authoring MCP server configured for your coauthoring session.

You can now use Canvas App skills like /canvas-app to create or edit your app.

To verify the setup, try: "List available Canvas App controls" — this should invoke list_controls.

來自 microsoft 的更多技能

oss-growth
microsoft
開源增長駭客角色
agent-framework-azure-ai-py
microsoft
使用Microsoft Agent Framework Python SDK(agent-framework-azure-ai)构建Azure AI Foundry代理。适用于使用AzureAIAgentsProvider创建持久化代理、使用托管工具(代码解释器、文件搜索、网络搜索)、集成MCP服务器、管理对话线程或实现流式响应。涵盖函数工具、结构化输出和多工具代理。
development
airunway-aks-setup
microsoft
在AKS上設定AI Runway——從裸叢集到執行模型。涵蓋叢集驗證、控制器安裝、GPU評估、供應商設定及首次部署。時機:「設定AI Runway」、「上線AKS叢集」、「安裝AI Runway」、「airunway設定」、「部署模型至AKS」、「在AKS上進行GPU推論」、「在AKS上設定KAITO」、「在AKS上執行LLM」、「在AKS上使用vLLM」、「在AKS上設定模型服務」、「AI Runway控制器」。
devops
appinsights-instrumentation
microsoft
使用Azure Application Insights檢測Web應用程式的指南。提供遙測模式、SDK設定與組態參考。適用時機:如何檢測應用程式、App Insights SDK、遙測模式、什麼是App Insights、Application Insights指南、檢測範例、APM最佳實踐。
devops
applicationinsights-web-ts
microsoft
使用Application Insights JavaScript SDK(@microsoft/applicationinsights-web)為瀏覽器/Web應用程式進行檢測。適用於真實使用者監控(RUM)——頁面檢視、點擊、AJAX/fetch依賴、例外、自訂事件,以及與後端OpenTelemetry追蹤關聯的瀏覽器端GenAI代理追蹤。涵蓋SDK載入器指令碼與npm設定、框架擴充(React、React Native、Angular)、點擊分析、遙測初始化器,以及從瀏覽器發出的代理/工具/模型span的OTel GenAI語意慣例。
devops
azure-ai-anomalydetector-java
microsoft
使用適用於 Java 的 Azure AI 異常偵測器 SDK 建置異常偵測應用程式。在實作單變量/多變量異常偵測、時間序列分析或 AI 驅動監控時使用。
development
azure-ai-language-conversations-py
microsoft
使用 azure-ai-language-conversations Python SDK 實作對話語言理解(CLU)。當使用 ConversationAnalysisClient 分析對話意圖與實體、建置 NLP 功能,或將語言理解整合至應用程式時使用。
development
azure-ai-ml-py
microsoft
Azure Machine Learning SDK v2 for Python。用於機器學習工作區、作業、模型、資料集、計算資源與管線。 觸發詞:「azure-ai-ml」、「MLClient」、「workspace」、「model registry」、「training jobs」、「datasets」。
development