> For the complete documentation index, see [llms.txt](https://docs.launchboard.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.launchboard.org/quick-projects/ai-chats-with-mcp+sqlite/quick-start-with-template.md).

# Quick Start with Template

{% embed url="<https://www.loom.com/share/de464644d1274e9f8ae0bf378262c620>" %}

Let's just get started by using the template to create your own working MCP server with an SQLite database that you can test in 3 steps. You can customize the MCP server and database after everything is working.

#### Step 1 - Create a new code repository from the template

Go to the code repository -> <https://github.com/launchboard/mcp-server-sqlite-template> and click the `Use this template` button in the upper right hand (shown below) and select `Create a new repository`

<div align="left" data-with-frame="true"><figure><img src="/files/qmT9kFrXMRfDxZ9Wv7vF" alt="" width="563"><figcaption></figcaption></figure></div>

Name your repository and choose private or public (either will work). Then click `Create repository` at the bottom to finish. This will be your code repository used for the MCP server that you will set up next.

#### Step 2 - Create a New FastMCP Cloud Server

Visit [fastmcp.cloud](https://fastmcp.cloud/) and sign in with your GitHub account. Then, create a project by choosing `Deploy from your code`. Each project corresponds to a GitHub repo, in this case you will choose the Github repo you just created from the template in step 1.&#x20;

<div align="left" data-with-frame="true"><figure><img src="/files/c3gNzWZrXW9hXP4kHJiW" alt="" width="563"><figcaption></figcaption></figure></div>

Select the repository you created in step 1 and click `Deploy [name of repo] →`

<div align="left" data-with-frame="true"><figure><img src="/files/hPmPCIFwSTn931NduqJv" alt="" width="563"><figcaption></figcaption></figure></div>

Give your server a simple name and use `server.py` as the entry point. Then, click `Deploy server`. Next you should see your server in the build process, like below.

<div align="left" data-with-frame="true"><figure><img src="/files/wxblLmZU7xouhfWu4L9X" alt="" width="563"><figcaption></figcaption></figure></div>

Once the build process is complete, there should be a green `production` label. If so, you are ready to test.

#### Step 3 - Test with ChatMCP

Now you can click `ChatMCP` at the top of the menu on the left to start a normal chat that has access to your MCP Server. Try *"What are the latest AI stories?"*. Since the template server has an SQLite database table of AI-related stories, the LLM can request the latest stories through the `get_latest_stories` tool on your server.

<div align="left" data-with-frame="true"><figure><img src="/files/WZmUyWiKWzYEXxQ590t7" alt="" width="563"><figcaption></figcaption></figure></div>

Next let's go through an [explanation of the template](/quick-projects/ai-chats-with-mcp+sqlite/template-explanation.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.launchboard.org/quick-projects/ai-chats-with-mcp+sqlite/quick-start-with-template.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.