> 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/developing-your-mcp-server.md). # Developing your MCP Server {% embed url="" %} Before developing your own database and MCP server: * Consider what interesting interactions you want to offer in your chat interface. * Understand the value each idea provides and balance it with how difficult it will be to implement it. * Sketch out your ideas as a flow chart, pseudo-code, or storyboard for reflection and refinement. It is recommended to generate at least three features (or tools) you can implement in your MCP server that are *simple, valuable, and complete*. ## Develop Your Server, Incrementally Once you have completed the [Quick Start with the Template](/quick-projects/ai-chats-with-mcp+sqlite/quick-start-with-template.md), make step-wise updates that allow you to test and debug along the way. Refer to the [template explanation](/quick-projects/ai-chats-with-mcp+sqlite/template-explanation.md) for technical help when making updates. Below is a suggested process you could follow. 1. **Create your CSV file for a database table.** If you intend to have multiple tables, start with just one. Ensure the formatting is correct, be mindful of special characters (e.g. commas, quotations, etc.), and be careful with empty values. 2. **Update the *****generate\_db.py***** program and generate your new database and table.** 3. **Update the *****server.py***** file with a correct title and database name.** 4. **Update/create one tool definition in the *****server.py***** file.** Start with the easiest one. 5. **Test your tool with the *****client.py***** program.** Debug if needed. 6. **Commit and push your changes in Github.** FastMCP cloud will automatically build your server for you. 7. **Test your new tool in the MCPchat.** If the chat doesn't go as expected, refine your tool description or SQL as needed. 8. **Repeat (back to step 4) for each tool.** ## Share Video Demos or Direct Access to Your Server coming ... --- # 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/developing-your-mcp-server.md?ask=&goal= ``` `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.