> ## Documentation Index
> Fetch the complete documentation index at: https://docs.dualentry.com/llms.txt
> Use this file to discover all available pages before exploring further.

# How to Connect Your AI Assistant to These Docs

> Connect Claude, Cursor, VS Code, or another AI tool to the DualEntry docs MCP server so it searches and cites these docs when it answers your questions.

Connect Claude, Cursor, or another AI assistant to the DualEntry docs MCP server, and it searches these docs and links to the pages it used when you ask how DualEntry works. There's nothing to install and no sign-in. Every client uses the same URL: `https://docs.dualentry.com/mcp`.

> [!NOTE]
>
> The docs MCP server only reads the public documentation, not your company's data. To let an assistant look up or post records in your DualEntry organization, connect the [DualEntry MCP server](https://docs.dualentry.com/accountants/ai-automation/mcp/mcp-quickstart.md) instead.

## Connect your AI assistant

Pick your client below and add the server.

**Claude**

Custom connectors need a Claude Pro, Max, Team, or Enterprise plan. On Team and Enterprise plans, an Owner adds the connector under **Organization settings > Connectors** first.

1. In Claude, go to **Customize > Connectors**.
2. Choose **Add**, then **Add custom connector**.
3. Enter a name, such as **DualEntry Docs**, and the URL `https://docs.dualentry.com/mcp`.

**Claude Code**

Run this in your terminal. Add `--scope user` before the URL to use it in every project.

```bash theme={null}
claude mcp add --transport http dualentry-docs https://docs.dualentry.com/mcp
```

**Cursor**

Choose the button to install with one click:

[![Add the DualEntry docs MCP server to Cursor](https://cursor.com/deeplink/mcp-install-dark.svg)](cursor://anysphere.cursor-deeplink/mcp/install?name=dualentry-docs\&config=eyJ1cmwiOiJodHRwczovL2RvY3MuZHVhbGVudHJ5LmNvbS9tY3AifQ==)

Or add this to `~/.cursor/mcp.json`, inside the existing `mcpServers` object if you already have one:

```json theme={null}
{
  "mcpServers": {
    "dualentry-docs": {
      "url": "https://docs.dualentry.com/mcp"
    }
  }
}
```

**VS Code**

Add this to `.vscode/mcp.json`, then start the server from the **MCP: List Servers** command:

```json theme={null}
{
  "servers": {
    "dualentry-docs": {
      "type": "http",
      "url": "https://docs.dualentry.com/mcp"
    }
  }
}
```

**OpenAI Codex**

Run this in your terminal:

```bash theme={null}
codex mcp add dualentry-docs --url https://docs.dualentry.com/mcp
```

**Other clients**

Add `https://docs.dualentry.com/mcp` as a remote MCP server using Streamable HTTP transport. No authentication is needed.

## Confirm it's connected

Ask your assistant something like *"How do I set up an approval workflow for bills in DualEntry?"* A working connection answers with links to docs pages such as [Approval Workflows](https://docs.dualentry.com/accountants/platform-configuration/approval-workflows.md). If it doesn't, check that the server is turned on in your client and ask it to use the DualEntry docs.

## Other ways to give an AI the docs

If your tool doesn't support MCP, you can hand it the docs directly:

* **One page**: choose **Copy page** in the menu at the top of any page to copy it as Markdown, then paste it into your AI tool.
* **The whole site**: give an AI tool that can browse the web the URL [`https://docs.dualentry.com/llms.txt`](https://docs.dualentry.com/llms.txt) instead of pasting anything. It's an index of every docs page, like a sitemap, so the tool can find and read the pages it needs.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.