> For the complete documentation index, see [llms.txt](https://docs.tonic.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.tonic.ai/fabricate/databases-and-data/simulations/simulation-mcp-servers.md).

# Using the built-in MCP servers to interact with the results

One use case for simulations is to generate realistic cross-application content that you can use to test agents.

To allow agents to interact with the simulation results, Fabricate provides a set of built-in MCP servers.

Each built-in MCP server is associated with a supported content platform. For example, there is an MCP server for Slack, an MCP server for Google Workspace, and an MCP server for Microsoft Outlook.

## Publishing built-in MCP servers <a href="#mcp-server-publish" id="mcp-server-publish"></a>

Before you can use a built-in MCP server to interact with a set of results for a specific content platform, you must publish the MCP server for those results.

To publish a built-in MCP server, prompt the Data Agent. You specify:

* The set of results to publish the MCP server for.
* The content platform to publish the MCP server for. You can only publish MCP servers for content platforms that are included in the results. For example, if your results do not include Outlook emails or calendars, then you cannot publish the Outlook MCP server for those results.

The MCP server is always published in the currently selected project version.

For example:

`Publish the Slack MCP server for the Product design workflow simulation results database.`

To publish all of the applicable MCP servers for a given set of results:

`Publish all of the built-in MCP servers that apply to the Product design workflow simulation results database.`

## Viewing the published MCP servers <a href="#mcp-server-view" id="mcp-server-view"></a>

The [**MCPs** page for a project version](/fabricate/data-agent-tools/project-api/mcp-servers.md) includes any published built-in MCP servers.

<figure><img src="https://4109733485-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FmoU4gTR9LxlzHeWmQCUZ%2Fuploads%2FL7iU28KxwQovTQ9LAeqR%2FProject_MCPBuiltInPublished.png?alt=media&amp;token=d4fdcd02-93f4-4a01-85a3-613c491ef845" alt=""><figcaption><p>MCPs page entry for a published built-in MCP server</p></figcaption></figure>

For each published MCP server, the list includes:

* The name of the MCP server.
* The product that it applies to.
* The set of simulations results that it applies to.
* The MCP server URLs for project versions and sandboxes.
* The list of available tools

For details on how to authenticate, click **How to authenticate**.

## Removing a published MCP server <a href="#mcp-server-remove" id="mcp-server-remove"></a>

To remove a published MCP server, click its **Delete** option.


---

# 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.tonic.ai/fabricate/databases-and-data/simulations/simulation-mcp-servers.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.