Andrew Ng's team has released "MCP: Building Context-Rich AI Applications with Anthropic".

Deep Learning.AIThe platform launched "MCP: Build Rich-Context" AI The online course "Apps with Anthropic" is developed by Anthropic and DeepLearning.AIThis collaboratively developed course, taught by Elie Schoppik, is at an intermediate level and lasts 1 hour and 38 minutes. It includes 11 video lessons and 7 code examples. The course primarily introduces the Model Context Protocol (MCP), guiding learners through hands-on practice to understand its core concepts, including its client-server architecture and communication mechanisms. The course covers how to transform a chatbot into an MCP-compatible application, build and deploy local or remote MCP servers, and connect chatbots to different MCP servers.

• Course NameMCP: Build Rich-Context AI Apps with Anthropic
• Course Level:intermediate
• Course duration1 hour 38 minutes
• Course Format11 video lessons, 7 code examples
• InstructorsElie Schoppik (Head of Technology Education at Anthropic)
• Course InstitutionDeepLearning.AI(Developed in collaboration with Anthropic)

• Standardized tools and data accessExploring how to standardize MCPAIApplications gain access to tools and data, simplifying the integration of new tools and connections to external systems (such as GitHub repositories, Google Docs, local files, etc.).
• Building and deploying MCP serversLearn how to build and deploy an MCP server that provides tools, resources, and tips, and add them to...AIApplications (such as)Claude To extend its functionality in the configuration of Desktop.
• Creating MCP-compatible applicationsBuild an MCP-compatible application that hosts multiple MCP clients, each maintaining a one-to-one connection with an MCP server.

• MCP architectureThis section introduces the client-server architecture and underlying communication mechanism of MCP.
• Chatbot ExamplesThis section demonstrates how to transform a chatbot into an MCP-compatible application through code examples.
• Create an MCP serverUse FastMCP to build a local MCP server and use MCP Inspector for testing.
• Create an MCP clientCreate an MCP client in the chatbot and dynamically connect to the server.
• Connect to the reference serverConnect the chatbot to reference servers built by the Anthropic team, such as file system servers and network content extraction servers.
• ConfigurationClaude DesktopLearn how to configureClaude Desktop allows you to connect to your server and other servers, and explore how it abstracts the underlying logic of the MCP client.
• Remote deployment serverLearn how to remotely deploy an MCP server and test it using Inspector or other MCP-compatible applications.
• Future development directionUnderstand the future development roadmap of MCP, including multiple...intelligentbodyArchitecture, MCP registry API, server discovery, authorization and authentication, etc.

Course official website address

• Official website address:https://www.deeplearning.ai/short-courses/mcp-build-rich-context-ai-apps-with-anthropic/

• Skill RequirementsFamiliar with Python and has a good understanding of...LLMTips andLLMI have a basic understanding of application development.
• Learning ObjectivesThe goal is to build a context-rich platform that can connect to the growing MCP server ecosystem.AIApplications that reduce the integration workload for developers.

• Highly practicalThrough code examples and hands-on practice, learners are helped.fastMaster the implementation and application of MCP.
• Ecosystem connectivityEmphasizing how toAIStandardize connections between applications and external data sources and tools to reduce fragmentation during the development process.
• Future OutlookIt provides guidance on the future development of MCP, enabling learners to understand and adapt to the development of new technologies in advance.

Cornell UniversityAI Agents vs. Agentic AIConcept Classification, Applications, and Challenges

Mary Meeker's team released "artificialintelligentTrend Report (PDF file) - AITutorial materials