🔒 Guided

Pre-launch preview. Authorised access only.

Incorrect code

Guided by A Guide to Cloud
Explore AB-900 AI-901 aws-aif-c01
Guided AB-620 Domain 2
Domain 2 — Module 5 of 12 42%
15 of 28 overall

AB-620 Study Guide

Domain 1: Plan and Configure Agent Solutions

  • Getting Started: Copilot Studio for Developers Free
  • Planning Enterprise Integration and Reusable Components Free
  • Identity Strategy for Agents Free
  • Channels, Deployment and Audience Design Free
  • Responsible AI and Security Governance Free
  • Agent Flows: Build, Monitor and Handle Errors Free
  • Human-in-the-Loop Agent Flows Free
  • Topics, Tools and Variables Free
  • Advanced Responses: Custom Prompts and Generative Answers Free
  • API Calls, HTTP Requests and Adaptive Cards Free

Domain 2: Integrate and Extend Agents in Copilot Studio

  • Enterprise Knowledge Sources: The Big Picture
  • Copilot Connectors and Power Platform Connectors
  • Azure AI Search as a Knowledge Source
  • Adding Tools: Custom Connectors and REST APIs
  • MCP Tools: Model Context Protocol in Action
  • Computer Use: Agent-Driven UI Automation
  • Multi-Agent Solutions: Design and Agent Reuse
  • Integrating Foundry Agents
  • Fabric Data Agents: Analytics Meets AI
  • A2A Protocol: Cross-Platform Agent Collaboration
  • Grounded Answers: Azure AI Search with Foundry
  • Foundry Model Catalog and Application Insights

Domain 3: Test and Manage Agents

  • Test Sets & Evaluation Methods
  • Reviewing Results & Tuning Performance
  • Solutions & Environment Variables
  • Power Platform Pipelines for Agent ALM
  • Agent Lifecycle: From Dev to Production
  • Exam Prep: Diagnostic Review

AB-620 Study Guide

Domain 1: Plan and Configure Agent Solutions

  • Getting Started: Copilot Studio for Developers Free
  • Planning Enterprise Integration and Reusable Components Free
  • Identity Strategy for Agents Free
  • Channels, Deployment and Audience Design Free
  • Responsible AI and Security Governance Free
  • Agent Flows: Build, Monitor and Handle Errors Free
  • Human-in-the-Loop Agent Flows Free
  • Topics, Tools and Variables Free
  • Advanced Responses: Custom Prompts and Generative Answers Free
  • API Calls, HTTP Requests and Adaptive Cards Free

Domain 2: Integrate and Extend Agents in Copilot Studio

  • Enterprise Knowledge Sources: The Big Picture
  • Copilot Connectors and Power Platform Connectors
  • Azure AI Search as a Knowledge Source
  • Adding Tools: Custom Connectors and REST APIs
  • MCP Tools: Model Context Protocol in Action
  • Computer Use: Agent-Driven UI Automation
  • Multi-Agent Solutions: Design and Agent Reuse
  • Integrating Foundry Agents
  • Fabric Data Agents: Analytics Meets AI
  • A2A Protocol: Cross-Platform Agent Collaboration
  • Grounded Answers: Azure AI Search with Foundry
  • Foundry Model Catalog and Application Insights

Domain 3: Test and Manage Agents

  • Test Sets & Evaluation Methods
  • Reviewing Results & Tuning Performance
  • Solutions & Environment Variables
  • Power Platform Pipelines for Agent ALM
  • Agent Lifecycle: From Dev to Production
  • Exam Prep: Diagnostic Review
Domain 2: Integrate and Extend Agents in Copilot Studio Premium ⏱ ~15 min read

MCP Tools: Model Context Protocol in Action

Connect to MCP servers for cross-platform AI tool integration.

The universal plug for AI agents

☕ Simple explanation

MCP is like USB-C for AI tools.

Remember when every phone had a different charger? USB-C fixed that — one standard plug that works everywhere. MCP (Model Context Protocol) does the same thing for AI agents and tools.

Before MCP, if you wanted your Copilot Studio agent to use a tool built for Claude, ChatGPT, or any other AI platform, you had to rebuild the integration from scratch. MCP is an open standard that lets any AI agent connect to any MCP-compatible tool server using the same protocol. Build a tool once as an MCP server, and every MCP-compatible agent can use it — Copilot Studio, GitHub Copilot, Claude, and more.

Copilot Studio supports MCP natively. You point it at an MCP server URL, select which tools to enable, and the agent can call them.

Model Context Protocol (MCP) is an open standard originally developed by Anthropic and now adopted across the AI industry. It defines a JSON-RPC 2.0-based protocol for AI agents to discover and invoke tools, access resources, and use prompt templates provided by external servers.

In the Copilot Studio context, MCP enables agents to connect to any MCP-compliant server — whether it is a custom-built internal tool, a third-party SaaS integration, or a community-built server. The protocol abstracts away the specifics of how the tool works; the agent only needs to know the server URL and authentication details.

MCP defines three capability types: tools (functions the agent can call), resources (data the agent can read), and prompts (reusable prompt templates). In Copilot Studio, tools are the primary integration point — the agent invokes MCP tools the same way it invokes custom connectors or REST API tools.

The transport layer uses Streamable HTTP for remote servers (SSE transport is deprecated), or stdio for local development. JSON-RPC 2.0 handles the request/response format. Note: MCP tools in Copilot Studio are currently in preview.

MCP vs everything else

The exam loves comparison questions. Know how MCP stacks up against the other tool mechanisms you have learned.

Tool integration mechanisms in Copilot Studio
FeatureProtocolCross-platformDiscoveryBest for
Custom connectorOpenAPI (Swagger) REST specPower Platform ecosystem only — does not work outside MicrosoftDeveloper manually selects actions during configurationReusable integrations within Power Platform and Copilot Studio
REST API toolDirect HTTP (any REST endpoint)Works with any HTTP API but configured per agentDeveloper manually defines endpoints and schemasQuick, direct API calls when no connector or MCP server exists
MCP toolJSON-RPC 2.0 over Streamable HTTP (Model Context Protocol)Cross-platform — same server works with Copilot Studio, GitHub Copilot, Claude, and othersAutomatic — agent discovers available tools from the server at connection timeCross-platform tool sharing, community tools, rapidly evolving tool ecosystems
A2A protocol (M20)Agent-to-Agent protocol over HTTPCross-platform agent orchestration (not tool invocation)Agents advertise capabilities via Agent CardsMulti-agent coordination across different AI platforms

How MCP works in Copilot Studio

The integration flow has four steps. Understand these and you can handle any MCP exam question.

Step 1 — Connect to the MCP server: In Copilot Studio, navigate to Tools and add a new MCP tool. Provide the server URL (the Streamable HTTP endpoint) and authentication details (API key, OAuth token, or none for development servers). Note that MCP tools are currently a preview feature.

Step 2 — Discover available tools: Copilot Studio calls the MCP server’s tools/list method. The server responds with a list of available tools, each with a name, description, and input schema. This is automatic — you do not need to manually define the tool shape.

Step 3 — Select and enable tools: From the discovered tools, you select which ones to enable for the agent. Not every tool on the server needs to be exposed — you choose what the agent can use.

Step 4 — Agent uses the tools: At runtime, the orchestrator sees the MCP tools alongside custom connectors and REST API tools. When the user’s intent matches a tool description, the orchestrator calls the MCP server’s tools/call method with the required inputs and receives the result.

💡 The three MCP capabilities

MCP defines three capability types, though Copilot Studio primarily uses the first:

  • Tools — Functions the server exposes for the agent to call (e.g., “analyseDocument”, “generateChart”, “queryDatabase”). This is what Copilot Studio integrates with.
  • Resources — Data endpoints the agent can read (similar to GET-only APIs). Think of these as read-only data sources the agent can access.
  • Prompts — Reusable prompt templates the server provides. The agent can use these as starting points for specific tasks.

For the AB-620 exam, focus on tools. Resources and prompts are part of the MCP spec but are less commonly tested.

Under the hood: JSON-RPC 2.0

MCP uses JSON-RPC 2.0 as its message format. You do not need to write JSON-RPC yourself — Copilot Studio handles the protocol — but understanding the format helps you debug and troubleshoot.

MethodWhat it doesExample
tools/listReturns all available tools from the serverAgent startup: “What tools do you have?”
tools/callInvokes a specific tool with parametersRuntime: “Call analyseDocument with this PDF URL”
resources/listReturns available data resourcesDiscovery: “What data can I read?”
resources/readReads a specific resourceRuntime: “Get the contents of this resource”
prompts/listReturns available prompt templatesDiscovery: “What prompt templates do you offer?”

The transport layer for remote servers uses Streamable HTTP (the SSE transport was deprecated in the March 2025 MCP spec revision). For local development, the stdio transport pipes data through standard input/output.

Scenario: Priya connects a document analysis MCP server

Priya’s recruitment agent at AgentForge needs to analyse CVs — extracting skills, experience years, education, and matching them against job requirements. Instead of building this capability from scratch, Priya finds a community MCP server called “doc-analyzer” that provides exactly these tools.

She adds the MCP server in Copilot Studio, entering the server URL (https://mcp.docanalyzer.io/mcp) and providing the API key. Copilot Studio calls tools/list and discovers three tools: extractSkills (extracts skills from a document URL), matchRequirements (compares extracted skills against a job description), and generateSummary (creates a candidate summary).

Priya enables all three tools. Now when a recruiter uploads a CV and says “Analyse this candidate for the Senior Developer role,” the orchestrator calls extractSkills to parse the CV, then matchRequirements to compare against the job posting, and finally generateSummary to present the results. Three MCP tool calls, zero custom code.

The beauty: if Priya later decides to switch to a different document analysis MCP server (maybe one with better accuracy), she just changes the server URL. The tool interface is standardised — no code changes needed.

💡 Exam tip: MCP is about cross-platform portability

When the exam asks why you would choose MCP over a custom connector, the answer is almost always cross-platform portability. A custom connector works only in the Power Platform ecosystem. An MCP server works with any MCP-compatible client — Copilot Studio, GitHub Copilot, Claude Desktop, VS Code, and more. If the scenario involves tools that need to work across multiple AI platforms, MCP is the answer.

Question

What is MCP and what problem does it solve?

Click or press Enter to reveal answer

Answer

Model Context Protocol (MCP) is an open standard for AI agent-to-tool communication. It solves the fragmentation problem — instead of building separate integrations for every AI platform, you build one MCP server and every MCP-compatible agent can use it.

Click to flip back

Question

What transport and message format does MCP use?

Click or press Enter to reveal answer

Answer

MCP uses JSON-RPC 2.0 as the message format. For remote servers, the transport is Streamable HTTP (SSE is deprecated). For local development, it uses stdio (standard input/output).

Click to flip back

Question

What are the three MCP capability types?

Click or press Enter to reveal answer

Answer

1. Tools — functions the agent can call to perform actions. 2. Resources — data endpoints the agent can read. 3. Prompts — reusable prompt templates. Copilot Studio primarily integrates with tools.

Click to flip back

Question

How does tool discovery work in MCP?

Click or press Enter to reveal answer

Answer

The agent calls the server's tools/list method. The server responds with a list of available tools, each with a name, description, and input schema. This is automatic — no manual definition needed.

Click to flip back

Question

Why would you choose MCP over a custom connector?

Click or press Enter to reveal answer

Answer

Cross-platform portability. A custom connector works only in the Power Platform ecosystem. An MCP server works with any MCP-compatible client — Copilot Studio, GitHub Copilot, Claude, VS Code, and others.

Click to flip back

Knowledge Check

Priya needs her Copilot Studio agent to use a document analysis tool that is also used by GitHub Copilot and Claude Desktop. Which integration mechanism should she choose?

Knowledge Check

When Copilot Studio connects to an MCP server, how does it learn what tools are available?

Knowledge Check

Which protocol format does MCP use for communication between the agent and the server?

🎬 Video coming soon

MCP Tools: Model Context Protocol in Action

← Previous

Adding Tools: Custom Connectors and REST APIs

Next →

Computer Use: Agent-Driven UI Automation

Guided

I learn, I simplify, I share.

A Guide to Cloud YouTube Feedback

© 2026 Sutheesh. All rights reserved.

Guided is an independent study resource and is not affiliated with, endorsed by, or officially connected to Microsoft. Microsoft, Azure, and related trademarks are property of Microsoft Corporation. Always verify information against Microsoft Learn.