Quick Start with Template
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
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 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.
Select the repository you created in step 1 and click Deploy [name of repo] →
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.
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.
Next let's go through an explanation of the template.
Last updated