Agentic AI describes systems that can plan multi-step work, use tools, maintain task context, and act within defined permissions. This program helps learners evaluate when that approach is appropriate and how to engineer it responsibly.

Do I need prior experience with AI agents to take this course?

No prior experience with agentic AI is required. The course begins by establishing when agents are the right approach, then moves into hands-on setup and building, so you gain both judgment and practical skills.

What will I get if I subscribe to this Certificate?

When you enroll in the course, you get access to all of the courses in the Certificate, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.

Tools, MCP Servers and External Integrations

3 days left! Get $70+ in savings and build skills with Coursera Plus. Save 40% for 3 months.

Tools, MCP Servers and External Integrations

This course is part of Building Agentic AI Apps with GitHub Copilot SDK Professional Certificate

Instructor: GitHub

Included with Learn more

5 modules

Gain insight into a topic and learn the fundamentals.

Intermediate level

Recommended experience

7 hours to complete

Flexible schedule

Learn at your own pace

5 modules

Gain insight into a topic and learn the fundamentals.

Intermediate level

Recommended experience

7 hours to complete

Flexible schedule

Learn at your own pace

What you'll learn

Construct custom tools with typed schemas that agents autonomously discover and invoke.
Configure MCP servers to give agents access to external data and services.
Implement least-privilege permission controls for agent tool invocations.
Build error-handling patterns that maintain agent workflow continuity.

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

11 assignments¹

AI Graded see disclaimer

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

Build your Software Development expertise

This course is part of the Building Agentic AI Apps with GitHub Copilot SDK Professional Certificate

When you enroll in this course, you'll also be enrolled in this Professional Certificate.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate from GitHub

There are 5 modules in this course

An agent that only generates text can't do real work. This course connects your agents to databases, APIs, and external services using custom tools and Model Context Protocol (MCP) servers, with the security controls to meet production demands. You'll define typed tool schemas that agents discover on their own, wire up local and remote MCP servers, enforce least-privilege permissions, and handle failures gracefully.

By the end, you'll be able to: - Build custom tools with typed schemas that agents invoke autonomously - Configure MCP servers for external data and service access - Implement least-privilege permission controls for tool calls - Build error-handling patterns that keep workflows running Tools include the GitHub Copilot SDK (Python and Node.js/TypeScript), MCP servers, the GitHub Copilot CLI, VS Code, and Git/GitHub.

Define and register custom tools that Copilot agents can autonomously discover and invoke during task execution. You'll learn to create tools with typed parameter schemas and return types, register them within sessions, and verify that agents correctly select and invoke your tools based on task requirements.

What's included

5 readings2 assignments

5 readingsTotal 51 minutes

Tool Schema Design Patterns & Best Practices5 minutes
Hands-on Activity: Define Three Custom Tools25 minutes
The Gap Between Definition and Invocation2 minutes
Verifying Tool Invocation & Debugging Selection4 minutes
Hands-on Activity: Register, Invoke & Debug a Tool Suite15 minutes

2 assignmentsTotal 45 minutes

Knowledge Check: Tool Definition & Schema Design15 minutes
Graded Quiz: Defining & Registering Custom Tools30 minutes

Configure Model Context Protocol (MCP) servers to give your agents access to external data sources and services. MCP is the SDK's primary extensibility mechanism for connecting agents to the outside world, databases, APIs, file systems, and third-party services. You'll learn to set up local and remote MCP servers and integrate them into Copilot sessions.

What's included

5 readings2 assignments

5 readingsTotal 52 minutes

MCP Configuration Reference & Server Catalog5 minutes
Hands-on Activity: Configure Local MCP Servers20 minutes
From Local Development to Production Connectivity 2 minutes
Integration Patterns & Security Basics5 minutes
Hands-on Activity: Integrate a Remote MCP Server20 minutes

2 assignmentsTotal 45 minutes

Knowledge Check: Understanding MCP & Local Server Configuration15 minutes
Graded Quiz: Integrating MCP Servers for External Data30 minutes

Implement permission controls that enforce least-privilege access for agent tool invocations. You'll learn to design approval workflows for sensitive operations, classify tools by risk level, and build permission handlers that give humans oversight of high-stakes agent actions. A critical production safety requirement for agentic systems

What's included

4 readings3 assignments

4 readingsTotal 25 minutes

Permission Design Patterns & Policy Templates4 minutes
Hands-on Activity: Build a Tiered Permission System15 minutes
The Role of Human Oversight in Sensitive Agent Operations2 minutes
Approval Workflow Implementation and Audit Logging4 minutes

3 assignmentsTotal 60 minutes

Knowledge Check: Permission Models & Least-Privilege Design15 minutes
Hands-on Activity: Design an Approval Workflow Specification15 minutes
Graded Quiz: Implementing Permission Controls for Tools30 minutes

Implement robust error handling for tool invocations that keeps agent workflows running when tools fail. You'll learn to design retry strategies, implement fallback tools, and build graceful degradation patterns that allow agents to continue producing useful results even when their tools encounter errors.

What's included

5 readings3 assignments

5 readingsTotal 45 minutes

Fallback Patterns & Implementation Reference4 minutes
Hands-on Activity: Implement Retry and Fallback Logic15 minutes
Partial Results are Better Than No Results2 minutes
Implementing Degradation & Error Reporting4 minutes
Hands-on Activity: Build a Degradation-Resilient Agent20 minutes

3 assignmentsTotal 60 minutes

Knowledge Check: Retry Strategies & Fallback Patterns15 minutes
Knowledge Check: Graceful Degradation & Workflow Continuity15 minutes
Graded Quiz: Error Handling & Tool Reliability30 minutes

Build a tool-integrated agent that combines custom tools, Model Context Protocol (MCP) server connectivity, permission controls, and error handling into a functioning data research assistant. This project integrates skills into a portfolio-ready deliverable that demonstrates production-grade tool management.

What's included

3 readings1 assignment

Earn a career certificate

Add this credential to your LinkedIn profile, resume, or CV. Share it on social media and in your performance review.

Instructor

GitHub

6 Courses5 learners

Offered by

GitHub

Explore more from Software Development

GitHub
Multi-Agent Orchestration and Application Integration
Course
GitHub
Sessions, Context and Conversational Agents
Course
GitHub
Production Readiness: Testing, Security and Deployment
Course
GitHub
Launching Your AI Agent Engineering Career
Course

Why people choose Coursera for their career

Felipe M.

Learner since 2018

"To be able to take courses at my own pace and rhythm has been an amazing experience. I can learn whenever it fits my schedule and mood."

Jennifer J.

Learner since 2020

"I directly applied the concepts and skills I learned from my courses to an exciting new project at work."

Larry W.

Learner since 2021

"When I need courses on topics that my university doesn't offer, Coursera is one of the best places to go."

Chaitanya A.

"Learning isn't just about being better at your job: it's so much more than that. Coursera allows me to learn without limits."

Break down barriers to learning with big savings
Get Coursera Plus
Start with easy savings for hard-working teams
Save 30% today

Frequently asked questions

This program is for software developers and ML engineers who are ready to apply agentic AI patterns and build with the GitHub Copilot SDK.

Comfort writing Python or Node.js/TypeScript, using Git, REST APIs, and command-line tools. LLM and prompt-engineering familiarity is helpful.

The GitHub Copilot SDK lets developers build applications that use Copilot's agentic capabilities. In this program, learners use the SDK with Python and Node.js/TypeScript to create, test, and evaluate agent workflows.

To access course materials, assignments, and earn a Certificate, you'll need to purchase the Certificate experience when you enroll in a course. Eligible learners may also have the option to start with a Free Trial. Some courses may also offer a Full Course, No Certificate option. This lets you access course materials, submit required assessments, and receive a final grade, but you won't be able to earn or purchase a Certificate.