> For the complete documentation index, see [llms.txt](https://docs.apryse.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.apryse.com/explore-docs-with-ai/connect-to-mcp.md).

# Connect to MCP

Retrieve documentation content without leaving your AI tool.

The Model Context Protocol (MCP) is an open standard that allows AI applications to connect to external data sources and tools.

When connected to the Apryse docs MCP server, AI assistants and coding agents can retrieve relevant documentation on demand as part of a conversation or task. Instead of relying on manual searches or shared links, they can access documentation directly, delivering more accurate answers, code examples, and troubleshooting guidance.

{% hint style="info" %}
**Info:** The MCP server provides AI tools with access to published Apryse SDK documentation, including product guides, tutorials, conceptual information, code examples, changelogs, and other documentation content available on the Apryse docs site.
{% endhint %}

### Discover the benefits

Connecting to an MCP server helps you:

* Access documentation directly from your AI tool.
* Find relevant content without manual searching or copy-and-paste.
* Reduce context switching between documentation and development environments.
* Use up-to-date documentation as context for AI conversations.
* Generate more accurate answers, code examples, and recommendations.
* Support coding, troubleshooting, and planning workflows.

### Decide when to use

MCP is best for users who regularly work in AI-powered tools and want documentation available directly within those workflows.

| Use MCP to                                                                                                               | Consider another option to                                                                                                                                   |
| ------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Access documentation directly from Claude Code, Codex, Cursor, GitHub Copilot, ChatGPT, or other MCP-compatible clients. | <p>Ask questions while browsing documentation.<br>→ Use <a href="/explore-docs-with-ai/chat-with-ai-assistant.md">AI Assistant</a></p>                       |
| Retrieve relevant documentation as part of coding, troubleshooting, and research workflows.                              | <p>Work with a specific documentation page in an AI tool.<br>→ Use <a href="/explore-docs-with-ai/access-docs-as-markdown.md">Markdown pages</a></p>         |
| Provide AI tools with up-to-date documentation through a direct integration.                                             | <p>Give AI tools a complete documentation export from a single file.<br>→ Use <a href="/explore-docs-with-ai/access-llms-full.txt.md">llms-full.txt</a></p>  |
| Build agent-based workflows that can search and reference documentation on demand.                                       | <p>Help AI tools discover documentation resources and site structure.<br>→ Use <a href="/explore-docs-with-ai/access-llms.txt.md">llms.txt</a></p>           |
| Reduce manual searching, copying, and sharing of documentation content.                                                  | <p>Quickly copy documentation content into an AI conversation.<br>→ Use <a href="/explore-docs-with-ai/access-docs-as-markdown.md">Markdown pages</a></p>    |
| Use documentation as a trusted reference while generating code or troubleshooting issues.                                | <p>Get broad documentation context without configuring an MCP client.<br>→ Use <a href="/explore-docs-with-ai/access-llms-full.txt.md">llms-full.txt</a></p> |

### Connect an AI client

You can connect any MCP-compatible client to the Apryse docs MCP server over streamable HTTP. Point the client to:

{% code overflow="wrap" expandable="true" %}

```
https://docs.apryse.com/~gitbook/mcp
```

{% endcode %}

The connection is supported via streamable HTTP only. `stdio` and `SSE` aren't supported.

### Next steps

We provide setup guides and examples for the following MCP-compatible AI clients:

* [Set up Claude Code](/explore-docs-with-ai/connect-to-mcp/set-up-claude-code.md)
* [Set up Codex](/explore-docs-with-ai/connect-to-mcp/set-up-codex.md)
* [Set up Cursor](/explore-docs-with-ai/connect-to-mcp/set-up-cursor.md)
* [Set up GitHub Copilot](/explore-docs-with-ai/connect-to-mcp/set-up-github-copilot.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.apryse.com/explore-docs-with-ai/connect-to-mcp.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.