Docs  \  AI  \  AI tools  \ 

Set up Kiro for agentic development with Power BI Desktop

This article describes how to configure Kiro so that an AI agent can read and modify a Power BI semantic model open in Power BI Desktop, and the report of a Power BI project.

The only requirement we assume is Power BI Desktop, already installed. Everything else is part of this setup.

Sample model used in all the steps: ContosoDemo10k.zip. Please, download it before you start.

At the end you have an agent in an editor that reads and writes the semantic model, and that also creates and validates report pages.

Kiro is the agentic development environment of Amazon Web Services, available as a desktop application and as a command-line client. This article covers the desktop application, because it has a panel for the MCP servers that makes the state of the connection visible.

Requirements

  • Power BI Desktop, installed.
  • Node.js 22 or later. The Power BI Modeling MCP server is started with npx, which is part of Node.js. Kiro does not need it for itself. A new machine does not have it, so step 1 installs it.
  • Windows 10 or Windows 11, 64 bit, for the desktop application. The command-line client of Kiro requires Windows 11.
  • An account to sign in: a GitHub account, a Google account, an AWS Builder ID, or an account of AWS IAM Identity Center. The free plan includes a monthly amount of credits, and the MCP servers are not a paid feature. Check the plans page before you start.
  • Git for Windows. The repository of the skills is downloaded with git, and Windows does not include it. Step 11 installs it.
  • Write permission on any semantic model you modify. The MCP server follows the same rules as the Power BI external tools.

MCP stands for Model Context Protocol. The Power BI Modeling MCP server runs on your machine and connects to Power BI Desktop like an external tool. Kiro is the client that hosts the agent, and it starts the server as a local process.

Back up your model before an agent writes to it. With the sample model, extract the archive again if something goes wrong.

Step 1: install Node.js

A new installation of Windows does not have it. npm and npx are part of Node.js, and the Power BI Modeling MCP server is started with npx.

Open the command prompt

Several steps of this article ask you to type a command. Windows has two programs that run the commands, and they are not interchangeable:

  • The command prompt. Press Windows+R, type cmd, and press Enter. The window shows a folder path followed by >.
  • PowerShell. Press Windows+R, type powershell, and press Enter. The line starts with PS.

Every command of this article says which of the two to use. To open a window already positioned in a folder, open that folder in File Explorer, type cmd in the address bar, and press Enter. When an installation asks for administrator rights, find Command Prompt in the Start menu, right-click it, and choose Run as administrator.

Install Node.js

Choose one of the two methods. LTS stands for Long Term Support.

Option 1: the installer. Download it from nodejs.org/en/download and run it.

Option 2: WinGet. In the command prompt:

winget install --id OpenJS.NodeJS.LTS --source winget

Both methods write in the folders of the machine, so they ask for administrator rights. If you do not have them, use one of the options at the end of this step.

Close the command prompt and open it again, so that it reads the updated path. Then verify the installation, in the command prompt:

node --version

The command returns the version you installed. The LTS installer provides 22 or later.

Install Node.js without administrator rights

These are options, not a replacement of the installer. Use one of them when the machine is managed and you do not have administrator rights. Each one writes in your user profile, and each one provides npm and npx.

Option 1: the standalone binary. The download page offers a standalone archive besides the installer. Extract it in a folder of your user profile, for example %LOCALAPPDATA%\nodejs, and add that folder to the Path variable of the user, in Settings > System > About > Advanced system settings > Environment variables. Nothing else is installed.

Option 2: fnm, the Fast Node Manager. It installs and switches the versions of Node.js in your user profile. Install fnm with WinGet, in the command prompt:

winget install Schniz.fnm

Add this line to your PowerShell profile, so that every session finds Node.js. The command notepad $PROFILE, typed in PowerShell, opens that file:

fnm env --use-on-cd --shell powershell | Out-String | Invoke-Expression

Open a new PowerShell window, install the LTS version, and read the version number it installed:

fnm install --lts

fnm list

Then set that version as the default, replacing <version> with the number of the LTS entry of the list:

fnm default <version>

Option 3: Scoop. It is a package manager that installs in %USERPROFILE%\scoop. Install it in PowerShell, in a window that is not elevated:

irm get.scoop.sh | iex

Then install Node.js, in the same PowerShell window:

scoop install nodejs-lts

With any of the three options, close the window, open a command prompt, and verify with node --version and npm --version.

Step 2: install Kiro

There is no Microsoft Store version.

Choose one of the two methods.

Option 1: the download page. Open kiro.dev/downloads, which offers the version for the x64 processors, and run the installer.

Option 2: WinGet. In the command prompt:

winget install -e --id Amazon.Kiro

The documentation of Kiro does not mention the package Amazon.Kiro, and the two channels can offer different versions. When they diverge, the download from the web page is the documented method.

If the installation with a script is blocked, allow the execution of the local scripts for your user (do not do that if the setup completed correctly). This command works only in PowerShell:

Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser

Please, do not start Kiro as an administrator, because the automatic update fails in that condition.

Step 3: open the sample model

  1. Download ContosoDemo10k.zip.
  2. Extract the archive in a local folder, for example C:\Demo. Please, do not open the file directly from the compressed folder.
  3. Open ContosoDemo10k.pbix in Power BI Desktop and leave Power BI Desktop open.

The title bar shows ContosoDemo10k. You use that name in step 6.

Step 4: open the application and sign in

  1. Start Kiro from the Start menu.
  2. Choose the provider in the welcome screen and sign in. The browser opens, you authenticate, and the control returns to the application.
  3. Open the folder of the sample, for example C:\Demo.

The autonomy of the agent has two modes, Supervised, which asks a confirmation for every action, and Autopilot, which proceeds inside the permissions. Keep Autopilot for this setup, in Settings > Agent > Agent Autonomy.

Step 5: register the Power BI Modeling MCP server

There is no extension to install. The server is an npm package, and Kiro starts it on demand.

Kiro reads two files: %USERPROFILE%\.kiro\settings\mcp.json, which applies to every folder, and .kiro\settings\mcp.json in the folder of the project. The two are merged, and the project wins where both declare the same server.

We use the file of the project. The Power BI Modeling MCP server is useful where you work on a model, and declaring it for the user loads it in every other session you open, for any other work. The file of the user remains the choice when you connect to Power BI Desktop from many folders.

  1. Open the Kiro panel and select the MCP Servers tab.
  2. Select Open Workspace MCP Config (JSON), which opens the file of the folder you opened in step 4, and creates it if it does not exist. The command palette, with Ctrl+Shift+P, reaches the same file with Kiro: Open workspace MCP config (JSON).

  3. Write this content:

    {
  "mcpServers": {
    "powerbi-modeling-mcp": {
      "command": "npx",
      "args": ["-y", "@microsoft/powerbi-modeling-mcp@latest", "--start", "--readonly"],
      "env": {},
      "disabled": false,
      "autoApprove": []
    }
  }
}
  4. Save the file. Kiro reconnects the servers when the file changes.

The --readonly argument blocks every write operation. We suggest it for the first session, so that a wrong prompt cannot modify anything. Step 8 replaces it.

The autoApprove array lists the tools that do not ask a confirmation. Leave it empty, so that every call is visible. The MCP Servers tab shows the state of each server, and the Output panel contains the entry Kiro - MCP Logs.

Step 6: connect to Power BI Desktop

Send this prompt:

Connect to 'ContosoDemo10k' in Power BI Desktop

The answer reports the model name and an active connection. The first call to the MCP server raises a confirmation prompt. Read it: it is the only checkpoint before a change.

Step 7: verify the connection

Send these two prompts to the agent, one after the other:

List the tables and their row counts
Show me the relationships in the model

Both answers arrive in a few seconds. The chain works: Kiro, MCP server, Power BI Desktop.

Step 8: enable the write operations

The session started in read-only mode, so the next prompt would fail. Remove the restriction:

  1. Open the Kiro panel and select the MCP Servers tab.
  2. Select Open Workspace MCP Config (JSON), which opens the file .kiro\settings\mcp.json of the project again.
  3. Remove "--readonly" from the args array and save.

Then send this prompt:

Create a measure that returns the Sales Amount of the previous year using the same format of the original measure.

The measure appears in Power BI Desktop without a refresh. Each write operation raises a confirmation prompt. The same approach applies to bulk operations, like format strings and display folders on hundreds of objects in a single request.

Step 9: enable the preview features for the report layer

The MCP server operates on the semantic model. The report layer requires a different tool, the Power BI report authoring skill, which works only on PBIP files in PBIR format. PBIP stands for Power BI Project, PBIR for Power BI enhanced report format. The skill cannot modify a .pbix file.

In Power BI Desktop, open File > Options and settings > Options > Preview features and enable these three options:

  • Power BI Project (.pbip) save option
  • Store reports using enhanced metadata format (PBIR)
  • Enable external tool access to Power BI Desktop through secure local APIs

The third option is the Power BI Desktop Bridge, and it is enabled by default. The report authoring skill uses it to reload the project and to capture a screenshot of a page, so that the agent verifies its own work. Verify that the option is checked.

Restart Power BI Desktop.

Step 10: save the sample as a project

Use File > Save as and choose the Power BI Project (*.pbip) file type. Power BI Desktop creates this structure:

ContosoDemo10k.pbip
ContosoDemo10k.SemanticModel/
ContosoDemo10k.Report/
.gitignore

The model is a set of TMDL files (Tabular Model Definition Language) and the report is a set of JSON files. Put the folder under source control and commit a baseline, so to undo a wrong operation with one command.

Step 11: install the report authoring skill

Git is required for this step. The repository is downloaded with git, and Windows does not include it. Install it, then close the command prompt and open it again.

Choose one of the two methods.

Option 1: the installer. Download it from git-scm.com/downloads/win and run it.

Option 2: WinGet. In the command prompt:

winget install --id Git.Git --source winget

The skills call two command-line tools. Install them in the command prompt:

npm install -g @microsoft/powerbi-report-authoring-cli@latest @microsoft/powerbi-desktop-bridge-cli@latest

The skill is part of the powerbi-authoring plugin of the skills-for-fabric repository, published by Microsoft. The plugin contains five skills: semantic model authoring, report planning, report design, report authoring, and report management.

Kiro is not named in the compatibility list of Microsoft, and it does not read the marketplaces published in the format of Claude Code. Kiro has its own agent skills, in the same SKILL.md format, so the installation is manual.

Clone the repository, in the command prompt:

git clone https://github.com/microsoft/skills-for-fabric.git C:\Demo\skills-for-fabric

Then copy the folders of the skills in the folder where Kiro discovers them, %USERPROFILE%\.kiro\skills for every project, or .kiro\skills for the current one, in the command prompt:

xcopy /E /I "C:\Demo\skills-for-fabric\plugins\powerbi-authoring\skills" "%USERPROFILE%\.kiro\skills"

Please, verify the folder names in the repository before you copy, because the layout changes between versions. The repository also has a skills folder in its root, which contains all the skills of the collection. The five skills of the report layer are the ones in the folder of the plugin. Each skill is a folder with a SKILL.md file, and the name of the folder must match the name written in that file.

Kiro also reads the AGENTS.md file in the root of a folder, and the repository publishes one, so cloning it inside the project adds the guidance without any other operation.

Restart Kiro and invoke a skill with / followed by its name.

This combination is not documented by Microsoft or by Kiro, and it can stop working with any update of the repository. Treat it as a manual installation and verify the result on the sample before you use it on a model that matters.

Step 12: connect the agent to the project

Open the folder that contains the .pbip file, so that the agent sees both the model folder and the report folder. When that is not the folder you opened in step 4, its .kiro\settings\mcp.json does not follow: copy the file in the new folder, or declare the server in the file of the user. Then send this prompt:

Open semantic model from PBIP folder 'C:\Demo\ContosoDemo10k.SemanticModel'

The MCP server manages the semantic model folder. The authoring skill reads and writes the report folder as files.

Step 13: create a report page

Create a report page with a line chart showing Sales Amount by Quarter, and a card showing the Sales Amount of the last year that has data.

Then ask the agent to validate the report, which checks the structure of the PBIR files, and open the .pbip file in Power BI Desktop. The skill runs this command, and you can run it yourself in the command prompt:

powerbi-report-author validate "C:\Demo\ContosoDemo10k.Report"

Save any manual change in Power BI Desktop before the agent iterates. The agent reads the files on disk and does not see the unsaved state. Editing in both places at the same time loses one set of changes.

The examples in the documentation use cards, bar charts, clustered column charts, tables, KPI cards, and slicers, and the skill converts the legacy card and matrix visuals into the modern cardVisual and pivotTable. There is no published list of the supported visuals, so expect some trial and error. Q&A, Bing maps, and filled maps are announced for deprecation, and Microsoft recommends avoiding them.

Configuration options

The command-line arguments of the MCP server go in the args array of the JSON entry.

Option Default Description
--start required Starts the server.
--readwrite enabled Allows write operations, each one with a confirmation.
--readonly   Blocks all the write operations.
--skipconfirmation   Removes the confirmation prompts.
--compatibility PowerBI Set it to Full for Analysis Services databases.
--authmode interactive Set it to serviceprincipal for unattended scenarios.

For the service principal authentication, set AZURE_CLIENT_ID and AZURE_TENANT_ID in the environment of the server, with either AZURE_CLIENT_SECRET or AZURE_CLIENT_CERTIFICATE_PATH.

On a model that matters, run the first session with --readonly, as in step 5.

Alternative installation methods

Manual installation. Download the VSIX package of the Visual Studio Code extension of the MCP server, rename it with the .zip extension, extract it, and configure the path of the executable. This avoids the download that npx performs at every start:

{
  "mcpServers": {
    "powerbi-modeling-mcp": {
      "command": "C:\\MCPServers\\PowerBIModelingMCP\\extension\\server\\powerbi-modeling-mcp.exe",
      "args": ["--start"],
      "disabled": false,
      "autoApprove": []
    }
  }
}

If npx does not start on Windows, use the command interpreter as the launcher:

{
  "mcpServers": {
    "powerbi-modeling-mcp": {
      "command": "cmd",
      "args": ["/c", "npx", "-y", "@microsoft/powerbi-modeling-mcp@latest", "--start"],
      "disabled": false,
      "autoApprove": []
    }
  }
}

The npx command is a .cmd script on Windows, and a process that starts it without a shell can fail to find it.

Limitations

  • The MCP server operates on the semantic model, not on the report.
  • The report authoring skill operates on PBIP projects in PBIR format, not on a .pbix file.
  • Neither of them can do anything your permissions do not allow, because they operate with your identity.
  • Model metadata does not stay local: table names, column names, measure definitions, and query results are sent to the language model of the service you signed in to.
  • The MCP server, the report authoring skill, and the Power BI Desktop Bridge are all in preview. Behavior and tools can change before general availability.
  • The agent proposes and executes. The review is your responsibility.
  • Run the MCP server natively on Windows. A server started through the Windows Subsystem for Linux is not supported by Kiro.
  • The report authoring skill has no marketplace installation for Kiro. The manual path of step 11 is not covered by the documentation of Microsoft or of Kiro.
  • The restrictions that an administrator applies to the MCP servers are enforced by the client, so they are not a security boundary on a machine where the user is an administrator.

Troubleshooting

The MCP server does not appear in the list of tools. Open the MCP Servers tab of the Kiro panel, verify that disabled is false, and read the Output panel, entry Kiro - MCP Logs. When you declared the server in the file of the project, verify that the folder open in Kiro is the one that contains .kiro\settings\mcp.json.

The server does not start and the message contains spawn npx ENOENT. Use the cmd form of the alternative installation methods, or the absolute path of the executable.

The automatic update of Kiro fails. Kiro was started as an administrator. Open the properties of the shortcut, tab Compatibility, and remove that option.

A skill does not appear. The name of the folder must match the name written in the SKILL.md file, in lowercase, with digits and hyphens only. Restart Kiro after the copy.

The npm or the npx command is not found. Node.js is not installed, or the terminal was opened before the installation. Close the terminal, open it again, and run node --version. See step 1.

The git command is not found. Git is not installed, or the command prompt was opened before the installation. Install Git for Windows as in step 11, then close the command prompt and open it again.

The server starts and provides no tools. Verify that Node.js is installed and that npx runs. The first start downloads the package, so it takes longer than the following ones. Run npx -y @microsoft/powerbi-modeling-mcp@latest --help once in the command prompt, so that the package is already in the cache.

Cannot connect to Power BI Desktop. The file must be open, and the name in the prompt must match the title bar: ContosoDemo10k, not ContosoDemo10k.pbix. After a restart of Power BI Desktop the port changes. Connect again.

The write operations are rejected. You need write permission on the model, and the server must not run with --readonly. See step 8.

The agent reports that a command is not available when it validates the report. Install the two command-line tools of step 11, @microsoft/powerbi-report-authoring-cli and @microsoft/powerbi-desktop-bridge-cli, then restart the client.

The report authoring skill does not modify the report. It requires PBIP in PBIR format. Verify both preview features and save the project again, because enabling PBIR does not convert a project already saved.

The report changes do not appear in Power BI Desktop. Reload the project. Power BI Desktop shows the version loaded before. Verify the preview option of the Power BI Desktop Bridge, so that the agent reloads the project without your intervention.

The agent modifies objects you did not mention. Name the objects explicitly. For example, “add display folders to the measures in the Sales table” instead of “apply the best practices”.

Conclusions

Install Node.js, install Kiro, declare the Power BI Modeling MCP server in mcp.json, open a model in Power BI Desktop, connect with one prompt.

These are the rules we suggest applying:

  • Keep autoApprove empty, so that every call of a tool is visible.
  • Read the Kiro - MCP Logs entry of the Output panel when a server does not connect.
  • Declare the server in the file of the project, so that it does not load in every other session you open.
  • Register the server by its package name, instead of asking the agent to find it.
  • Verify the connection with a read-only prompt before any change.
  • Keep a backup of the model, or work on a PBIP project under source control.
  • Read the confirmation prompts.
  • Use --readonly for the first session on a model that matters.
  • Do not write the connection port in a script.
  • Open the folder of the project in the client, so that the model and the report are both visible to the agent.
  • For the report layer, use PBIP with PBIR, and save in Power BI Desktop before the agent iterates.

References

The content of this article was verified in September 2026, with the @microsoft/powerbi-modeling-mcp package installed from npm with the @latest tag. Command names, preview settings, and plan boundaries change over time, so the linked documentation is the authority.

Last update: Sep 13, 2026
In this page