Skip to main content

Introduction

What is the Model Context Protocol (MCP)?​

The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources or tools. Whether you are building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need.

An MCP server is a lightweight program that exposes specific capabilities through the standardized Model Context Protocol (MCP). Host applications—such as chatbots, IDEs, and other AI tools—act as MCP clients, maintaining one-to-one connections with MCP servers. Common MCP clients include agent-based AI coding assistants (e.g., Q Developer, Cline, Cursor, Windsurf) and chatbot applications (e.g., Claude Desktop). MCP servers can access both local data sources and remote services to provide additional contextual information, improving the quality and accuracy of model outputs.

Features of MCP​

  • Zero-ops: Requires almost no additional configuration.
  • Plug-and-play: Can be directly invoked within IDEs, agents, or enterprise workflows.
  • Standardized calls: Avoids redundant integrations with different interfaces.

Advantages of MCP​

  • Improved output quality: By directly providing relevant context within the model’s environment, MCP servers significantly enhance the accuracy of model responses in specialized domains. This approach reduces hallucinations, improves technical precision, and enables more accurate code generation.
  • Access to the latest documentation: Foundation models may not be aware of the latest versions, APIs, or SDKs. MCP servers bridge this gap by incorporating up-to-date documentation, ensuring that your AI assistant always uses the most current features.
  • Workflow automation: MCP servers convert common workflows into tools directly usable by foundation models, allowing AI assistants to execute complex tasks with greater accuracy and efficiency.
  • Domain expertise: MCP servers provide deep contextual knowledge that may not be fully captured in a model’s training data, resulting in more accurate and useful responses for cloud development and specialized tasks.