> For the complete documentation index, see [llms.txt](https://docs.aiandbusiness.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aiandbusiness.com/tools-and-tech/ai-agent-tools/agent-to-agent-protocol/model-context-protocol-mcp.md).

# Model Context Protocol (MCP)

## What is Model Context Protocol (MCP)?

**Model Context Protocol (MCP)** is an open standard protocol developed by Anthropic that enables AI models to seamlessly connect with external data sources, tools, and APIs, enhancing their capabilities beyond their original training data.

{% embed url="<https://modelcontextprotocol.io/introduction>" %}

***MCP Clients***

{% tabs %}
{% tab title="Cursor" %}
<https://www.cursor.com/>
{% endtab %}

{% tab title="Claude" %}
[https://claude.ai/](https://claude.ai/login?returnTo=%2F%3F)
{% endtab %}
{% endtabs %}

***MCP Servers Collections***

{% hint style="warning" %}
Please note that some current MCP tools contain malicious programs, which may lead to serious security issues. Please exercise caution and identify them carefully.
{% endhint %}

{% tabs %}
{% tab title="Cursor Directory " %}
Cursor Directory <https://cursor.directory/>
{% endtab %}

{% tab title="Collection-Awesome MCP Servers" %}
A collection of MCP servers.

<https://github.com/punkpeye/awesome-mcp-servers>
{% endtab %}

{% tab title="MCP.so" %}
<https://mcp.so/>
{% endtab %}
{% endtabs %}

#### *Other*

{% tabs %}
{% tab title="Mem0" %}
Mem0 is a self-improving memory layer for LLM applications, enabling personalized AI experiences that save costs and delight users.

<https://mem0.ai/>

Github Link: <https://github.com/mem0ai/mem0/tree/main>
{% endtab %}

{% tab title="Second Tab" %}

{% endtab %}
{% endtabs %}

### Updates：

Microsoft MarkItDown now offers an MCP (Model Context Protocol) server for integration with LLM applications like Claude Desktop.&#x20;

<https://github.com/microsoft/markitdown?tab=readme-ov-file#markitdown>

***

***Must Read:***

<https://a16z.com/a-deep-dive-into-mcp-and-the-future-of-ai-tooling/>

<https://norahsakal.com/blog/mcp-vs-api-model-context-protocol-explained/>

<https://blog.replit.com/everything-you-need-to-know-about-mcp>