AI Agents for Power Automate

We are seeing a very strong interest and response in our release of Flow Studio MCP. So we want to get the word out more.

AI is rapidly moving beyond summary chatbots.
The next phase is AI agents — systems that can reason, decide, and take real actions inside software systems.

But agents need one critical capability:

AI Agents Needs Tools

Without tools, an AI agent is just a very articulate observer.

This is where MCP (Model Context Protocol) comes in — and why Power Automate is uniquely positioned to become an agent assisted - automation platform.

What is MCP

The Model Context Protocol (MCP) is an open standard designed to connect AI models with real tools and data sources.

Instead of hard-coding integrations, MCP provides a standard interface where AI systems can:

• Discover tools

• Call actions

• Retrieve context

• Execute operations

Technically, MCP works as a client–server architecture:

Component	Role
MCP Host	The AI system (agent)
MCP Client	Connector used by the agent
MCP Server	Provides tools and resources

This architecture allows any AI agent to connect to any MCP server without custom integration work.

MCP provides the structured way for agents to discover and call these tools safely.

• Without tools, AI is advice.

• With tools, AI becomes automation.

Why Power Automate Is Perfect for Agents

Power Automate already solves the hardest part of automation:

Connecting systems together.

It provides:

• 1000+ connectors

• workflow orchestration

• authentication handling

• retry logic

• error handling

• enterprise security

Power Automate is already used to automate business processes across apps and services.

Now imagine an AI agent that can:

• Create flows

• Debug flows

• Monitor flows

• Trigger flows

• Modify flows

Suddenly Power Automate becomes:

The action layer for AI agents.

Instead of coding integrations from scratch, agents can orchestrate real work through flows.

Demo Scenario: An Agent Creating a Flow

Imagine this conversation with an AI agent:

User

Create a flow that watches SharePoint for new files and posts them to Teams.

Agent reasoning

1. Understand the requirement

2. Generate a Power Automate flow definition

3. Call the MCP tool: createFlow

4. Deploy the workflow

Result:

A fully functional Power Automate flow created by an AI agent.

Even more interesting:

The agent could later:

• analyze failed runs

• repair broken connectors

• suggest optimizations

• deploy improved versions

How Flow Studio MCP Works

Flow Studio exposes Power Automate capabilities through an MCP server.

This allows AI agents to interact with flows programmatically.

Typical tools exposed include:

Tool	Purpose
List flows	Discover automation assets
Get flow runs	Inspect execution history
Review failures	Diagnose issues
Create flows	Generate automation
Update flows	Apply fixes

AI agents connect to the server like this:

{
  "mcpServers": {
    "flowstudio": {
      "url": "https://mcp.flowstudio.app/mcp",
      "headers": {
        "x-api-key": "YOUR_API_KEY"
      }
    }
  }
}

Once connected, an agent can operate Power Automate like a human maker — but faster and continuously.

This opens new possibilities:

• Self-healing automation

• AI operations for flows

• Automated governance

• AI-assisted development
  

The Bigger Vision - AI Agent Automation

Historically, automation platforms were built for humans.

Agents change that.

In the emerging architecture:

LayerTechnologyReasoningLLM / AI AgentToolsMCPExecutionPower AutomateSystemsMicrosoft 365, APIs

Flow Studio sits at the intersection:

bringing agent intelligence to Power Automate systems.

Instead of manually debugging workflows or writing scripts, agents can:

• monitor automation health

• investigate failures

• recommend fixes

• deploy improvements

All automatically.

Try It With Flow Studio MCP

You can connect AI agents to Power Automate today using Flow Studio MCP.

It exposes Power Automate capabilities as tools that agents can use.

Examples:

list-flows
inspect-failed-runs
create-flow
update-flow

This means an AI agent can:

• diagnose broken flows

• analyze run failures

• build new automation

• maintain existing systems

Get started here:

👉 https://mcp.flowstudio.app

Final Thoughts

AI agents will not replace automation platforms.

They will drive them.

Power Automate already provides the workflows. You already have more than enough Power Automate flows that you can’t monitor and manage. Your Agent will help you with that.

MCP provides the bridge between AI reasoning and real systems.

Together they unlock a new category of software:

AI-operated automation platforms.

And that is exactly what Flow Studio MCP enables.

We are seeing the beginning of a crazy wave. Ride this out with us!

Announcing Flow Studio MCP

We are introducing our favourite new child to the Flow Studio family of tools. This is Flow Studio MCP.

Flow Studio MCP is a purpose-built MCP server that lets GitHub Copilot, Claude, and other AI agents build, deploy, debug, and monitor Power Automate cloud flows programmatically.

You can get started as quickly as:

1. Start a trial

2. Grant Flow Studio permission to access your Power Automate platform

3. Copy the generated x-api-key and pass it to your agent to setup MCP

When you give agents much broader access to Power Automate platform, there are a bunch of scenarios we now have. These are some ideas that your agent can now assist you to do:

Maker

You can ask your Agent to build new flows based on existing ones. Ask it to change email template across every flow. Ask it to switch connection references. Rename compose or other glaring problems. Insert Compose blocks or Note text to help you remember the logic. Update description on every flow.

Operator

You can ask your Agent to monitor key business critical flows. Dive and debug the issue. Generate operational reports. You can ask agent to review critical approval workflow runs and generate Gantt chart view of key approval dates.

Support

Your agent can help you debug flows quickly. You can tell agent to quickly find the failed runs and find the error. Explain it to you, then offer suggestions on how to fix it.

Dev Ops

You can ask Agent to review different environments between DEV, UAT and PROD, compare the differences, and tell you if you didn’t bring a critical production hotfix back into DEV.

Administrator / COE

You can ask Agent to help you review COE issues, connections. We all know COE is unmanageable. Use an Agent to help you bring it under control.

You can also read about Catherine’s story of how we came to realize we can build a Flow Studio MCP and keep an eye out for our demo YouTube videos that we’ll be putting out.

Flow - lightweight fast template engine using Split twice

Technique 2 — Building a Lightweight Template Engine (Using Split Twice)

Take this example (using a handle-bar stil syntax)

ABC {{def}} GHI {{jkl}} MN

Using a dictionary (Compose)

{
  "def": "fish 🐟",
  "jkl": "chips 🍟"
}

We want to build a mini-template engine.
Now you might think - ah ok, let’s get some variables in here.

But John really dislikes variables in fact most of these flow hacks are how to not use variables. So how do you do this without variables?

1. Split on {{

split(outputs('Compose'), '{{')

result

[ 
  "ABC ",
  "def}} GHI ",
  "jkl}} MN"
]

2. Split each on }}

inside each item, split again

split(item(),'}}')

So now our original string becomes either:
["ABC "]

or

["def"," GHI "]

Recap, combine step 1 and 2

Select:
  from: split(outputs('Compose'), '{{')
  item: split(item(), '}}')

3. Conditional replacement using dictionary lookup

if(
  equals(length(item()),2),
  concat(
    outputs('Dictionary')?[item()?[0]],
    item()?[1]
  ),
  item()?[0]
)

Hidden insight

So the trick is this. If the row has 2 elements, that means the first element is a token, the rest is the remainder. If the row has only 1 element - then just return that.

[
  item()[0],
  dictionary[item()[0]] item()[1],
  dictionary[item()[0]] item()[1]
]
==>
[
  "ABC",
  "fish 🐟 GHI",
  "chips 🍟 MN"
]

If you want your dictionary lookup to be case insensitive, you can add toLower() to wrap around item()?[0]

4. Join it all together

join(body('Select'),'')

Result

ABC fish 🐟 GHI chips 🍟 MN

No loops.
No apply-to-each.
No regex.
No variables.
Super fast zero-second action.

This technique lets you:

• Build dynamic email templates

• Create server-side HTML rendering logic

• Replace merge fields safely

• Do token replacement in Dataverse text

• Build dynamic document generators

All using standard Power Automate expressions.

About: The old trigger URL will stop working on November 30, 2025

Starting in August 2025, we’ve begun to see this warning a lot in our Power Automate flows that uses HTTP Request (or Team Webhook) triggers.

“The old trigger URL will stop working on November 30, 2025. Your tools that use this flow WILL break unless you update them with the new URL.”

The old url uses the logic app domain:

https://*.logic.azure.com/workflows/{flow-name}/triggers/manual/paths/invoke

The new URL uses a largely undocumented api.powerplatform.com domain.

https://{environment-name}.environment.api.powerplatform.com/powerautomate/automations/direct/workflows/{flow-name}/triggers/manual/paths/invoke

Why New URL?

The NEW URL looks to be more future proof and ties the invoke URL to the environment and flow name within Power Platform, rather than the underlying logic apps infrastructure.

Microsoft’s documentation is here: Changes to HTTP or Teams Webhook trigger flows

Flow Studio new feature: Flow (Request) Report

To help with updating these URLs, we decide to put in a special View and Report for this in Flow Studio. Here, we are doing 4 things:

• This report shows flows that use the "When an HTTP request is received" trigger. These flows can be triggered externally via HTTP requests, making them suitable for integration scenarios.

• First we do a scan of all the environments and find all your flows that use this trigger. This may take a few minutes depending on the number of environments and flows.

• Then for each flow we will need to check the flow definition to extract the old and new request URL and method.

• We also need to check the flow's run history to see if it has been triggered recently. This will help us identify active flows.

View fullsize

We present this in a quick table for you to browse, but also provide an Export to Excel functionality so you can decide how you want to tackle the list.

Permissions

Because of the API access we need to read definition and trigger callback URL, this is not a scan we can do at the admin level - it has to be the owner of the flows.

You can find this new feature in our dev build:
https://dev.flowstudio.app

Diff Mode in Flow Studio

We are happy to introduce a new feature update in Flow Studio app. “Diff Mode”

• Navigate to Diff on the left hand side.

• Use the top dropdowns to select your environment, flow and (optionally) version. Hit “Load”

• You can use Monaco (VS Code) editor to copy Flow definition differences to the right hand side.

• The left hand side is always read-only.

• Clicking “Save” will save the right hand side flow definition.

This is a feature previously hidden in “Snapshots” and “Diff” flow. But that experience only lets you compare between the flow and its previous versions. The new experience also let you compare a flow between two different environments. So if you have Dev, Test and Prod environments with unmanaged solutions - you may need this to keep your flows in sync.

Do test this out in https://dev.flowstudio.app v1.3.58 for now and give us your feedback. We’ll aim to push this to production build within 1 week.

Thank you for supporting Flow Studio App