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

# Connect via MCP

VergeOS Docs publishes a hosted **MCP (Model Context Protocol) server**. Connect it to an AI assistant — Claude, Cursor, VS Code Copilot, Codex, and others — and that assistant can search and read this documentation directly while it helps you, instead of guessing or relying on stale training data.

{% hint style="info" %}
You need a client that supports **remote MCP servers over HTTP**. The server is public, so no API key or sign-in is required.
{% endhint %}

## The server

|                    |                                      |
| ------------------ | ------------------------------------ |
| **URL**            | `https://docs.verge.io/~gitbook/mcp` |
| **Transport**      | Streamable HTTP                      |
| **Authentication** | None (public)                        |

## Add the server

{% tabs %}
{% tab title="Claude Code" %}
Run the CLI command to add it for your user account:

```bash
claude mcp add vergeos-docs --scope user --transport http https://docs.verge.io/~gitbook/mcp
```

Then confirm it connected:

```bash
claude mcp list
```

{% endtab %}

{% tab title="Claude Desktop" %}

1. Open **Settings → Connectors**.
2. Choose **Add custom connector**.
3. Name it `VergeOS Docs` and set the URL to:

   ```
   https://docs.verge.io/~gitbook/mcp
   ```
4. Save, then enable the connector in a new chat.
   {% endtab %}

{% tab title="Cursor" %}
Add the server to `~/.cursor/mcp.json` (global) or `.cursor/mcp.json` (per project):

```json
{
  "mcpServers": {
    "vergeos-docs": {
      "url": "https://docs.verge.io/~gitbook/mcp"
    }
  }
}
```

{% endtab %}

{% tab title="VS Code" %}
Use the one-click install link:

```
vscode:mcp/install?%7B%22name%22%3A%22VergeOS%20Docs%22%2C%22url%22%3A%22https%3A%2F%2Fdocs.verge.io%2F~gitbook%2Fmcp%22%7D
```

Or add it manually to `.vscode/mcp.json`:

```json
{
  "servers": {
    "VergeOS Docs": {
      "url": "https://docs.verge.io/~gitbook/mcp"
    }
  }
}
```

{% endtab %}

{% tab title="Codex" %}
Run the CLI command:

```bash
codex mcp add vergeos-docs --url https://docs.verge.io/~gitbook/mcp
```

{% endtab %}
{% endtabs %}

## What you get

Once connected, the assistant gains two tools:

* **`searchDocumentation`** — search across all VergeOS Docs and return matching content with direct page links.
* **`getPage`** — fetch the full Markdown of a specific documentation page.

## Try it

Ask your assistant something that should pull from the docs, for example:

{% hint style="success" %}

* "Search the VergeOS docs for how to configure a site sync."
* "Using the VergeOS docs, summarize the steps to migrate a VM from VMware."
* "What does the VergeOS documentation say about node sizing for an edge deployment?"
  {% endhint %}

If the tools are available and answers cite VergeOS Docs pages, the connection is working.

## Go further with agent skills

The MCP server gives an assistant read access to the docs. If you use **Claude Code** or **Codex**, the [VergeOS agent skills](/work-with-ai-tools/agent-skills.md) package adds task-focused workflows on top — troubleshooting, diagnostics, training, and infrastructure management through the `vrg` CLI — and bundles this same docs MCP server for you.


---

# 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:

```
GET https://docs.vergeos-demo.com/work-with-ai-tools/connect-via-mcp.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.