> For the complete documentation index, see [llms.txt](https://docs.playai.network/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.playai.network/playhub/into-the-mcps.md).

# Into the MCPs

### **What are MCPs?**

MCP (Model Context Protocol) is an open standard that enables secure and structured communication between AI models, applications, and external data sources or tools. MCP servers provide services or functionalities (e.g., integrations, task execution, or enhanced AI model features) that can be accessed by MCP clients like PlayHub or Aura.

Key Features of MCP:

* **Standardized Communication:** MCP defines how clients and servers exchange data for consistency across different implementations.
* **Extensibility:** New functionalities can be added without disrupting existing systems.
* **Security by Design:** MCP ensures secure data handling and access control.

### General architecture <a href="#general-architecture" id="general-architecture"></a>

At its core, MCP follows a client-server architecture where a host application can connect to multiple servers:

<figure><img src="/files/U0XBy6O6IA1JCZfdCGtF" alt=""><figcaption></figcaption></figure>

* **MCP Hosts**: Programs like Claude Desktop, IDEs, or AI tools that want to access data through MCP
* **MCP Clients**: Protocol clients that maintain 1:1 connections with servers
* **MCP Servers**: Lightweight programs that each expose specific capabilities through the standardized Model Context Protocol
* **Local Data Sources**: Your computer’s files, databases, and services that MCP servers can securely access
* **Remote Services**: External systems available over the internet (e.g., through APIs) that MCP servers can connect to

### **AI Workflows with MCPs**

Workflows are designed to handle specialized, complex tasks and automations, reducing the need for users to constantly provide prompts. These workflows become even more powerful when integrated into the MCP ecosystem, where they can interact with other MCP servers and applications.

By leveraging MCP services, workflows can adapt to diverse contexts, enhancing their capabilities and ensuring seamless collaboration across tools and applications. This transforms them into highly flexible, efficient, and productive components of a unified system.