> For the complete documentation index, see [llms.txt](https://docs.datasentinel.io/manual/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.datasentinel.io/manual/ai-connector/analyze-and-tune-workloads/work-with-several-platforms.md).

# Work with several platforms

Connect several Datasentinel platforms to one assistant, switch between them, and get an overview across all of them.

Many teams operate more than one Datasentinel platform: production and staging, one platform per region, or one per datacenter. Each platform runs its own MCP server, and your assistant can register all of them side by side. One conversation then reaches every platform you operate: pick one, switch when you need to, or ask for an overview across all of them.

**Example prompts:**

* "List my Datasentinel platforms with their status."
* "Switch to the production platform and show the top 5 instances by workload over the last hour."
* -> "Do the same for the staging platform"
* "On the staging platform, compare the application crm workload with its production twin."

## One platform, one MCP server

Every platform server exposes its own MCP endpoint (see [MCP Server Setup](/manual/ai-connector/server-setup/mcp-server-setup.md)). To work with several platforms, register one MCP server entry per platform in your assistant, exactly as the [configure guides](/manual/ai-connector/connect-a-cli-assistant/configure-claude-code.md) show for a single one.

Name every entry with the `datasentinel-` prefix and a distinct suffix per platform: `datasentinel-prod`, `datasentinel-staging`, `datasentinel-eu`, and so on. The Datasentinel Skill discovers platforms by this prefix, so one Skill install serves them all. Adding a platform is just one more MCP entry in the assistant: the Skill needs no change.

For example, with Claude Code:

```bash
claude mcp add --scope user --transport http datasentinel-prod https://prod-host/mcp
claude mcp add --scope user --transport http datasentinel-staging https://staging-host/mcp
```

To verify what the Skill sees, run `/datasentinel platforms`: it lists every platform discovered by the prefix.

{% hint style="info" %}
**One login, one sign-in per platform.** Each platform is signed in separately, the first time the assistant uses it, with the same login and password if your account exists on every platform. The sessions are independent, and `datasentinel whoami` shows which platform the current session uses and who you are signed in as there.
{% endhint %}

{% @arcade/embed url="<https://app.arcade.software/share/PvEPECJA6sD4IxgZLi3D>" flowId="PvEPECJA6sD4IxgZLi3D" %}

*This walkthrough was recorded with the Claude Desktop app.*

## How the assistant picks a platform

Multiple platforms never make the conversation ambiguous, because the Skill follows a few simple rules:

* If your request names a platform, or only one is configured, it is used directly.
* If several platforms match, the assistant lists the candidates and asks which one to use.
* The chosen platform is remembered for the rest of the session: the assistant never switches silently.
* To change platform, just say so: "switch to the staging platform" is enough.

## A view across your platforms

You can also step above any single platform:

* **Fleet-wide status:** ask for the status of all platforms and the assistant checks each one in a single pass.
* **Cross-platform comparisons:** ask it to compare an instance or a workload on one platform with its counterpart on another, for example production against staging after a release.

For analyses across many instances of a **single** platform (selected by tag), see [Analyze across multiple instances](/manual/ai-connector/analyze-and-tune-workloads/analyze-across-instances.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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.datasentinel.io/manual/ai-connector/analyze-and-tune-workloads/work-with-several-platforms.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.