Configure Canvas Mcp logo

Configure Canvas Mcp

Organization
microsoft
configure-canvas-mcp

Configure the Canvas Authoring MCP server for the current coauthoring session. USE WHEN "configure MCP", "set up MCP server", "MCP not working", "connect Canvas Apps MCP", "canvas-authoring not available", "MCP not configured", "set up canvas apps".

Overview

Publishermicrosoft
Repositorypower-platform-skills
Skill nameconfigure-canvas-mcp
Stars
895
Forks
182
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by microsoft on GitHub. Read the source before you install it.

Installation

Install the Configure Canvas Mcp AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/microsoft/power-platform-skills.git /tmp/power-platform-skills
mkdir -p .claude/skills
cp -r /tmp/power-platform-skills/plugins/canvas-apps/skills/configure-canvas-mcp .claude/skills/configure-canvas-mcp
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Configure Canvas Mcp in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Configure Canvas Mcp on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Configure Canvas Mcp is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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:

bash
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.

Frequently asked questions

What does the Configure Canvas Mcp AI skill do?

Configure the Canvas Authoring MCP server for the current coauthoring session. USE WHEN "configure MCP", "set up MCP server", "MCP not working", "connect Canvas Apps MCP", "canvas-authoring not available", "MCP not configured", "set up canvas apps".

Why use Configure Canvas Mcp on TypingMind?

Because you install it once and use it with any model. Configure Canvas Mcp is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Configure Canvas Mcp in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/microsoft/power-platform-skills/tree/main/plugins/canvas-apps/skills/configure-canvas-mcp. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Configure Canvas Mcp?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Configure Canvas Mcp?

As many as you like. As long as a model supports skills, you can use Configure Canvas Mcp with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Configure Canvas Mcp AI skill free?

Yes. It is published on GitHub by microsoft under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇