AI Services/Mcp Service Creation
Step-by-step guide to creating an MCP (Model Context Protocol) server service in DreamFactory for AI assistant integration
Creating an MCP Server Service
Quick Reference
| Property | Value |
|---|---|
| Service Type | MCP Server |
| Required Fields | API Name, Database Service |
| Auto-Generated | OAuth Client ID, OAuth Client Secret |
| Authentication | OAuth 2.0 |
| Supported AI Clients | ChatGPT, Claude, Cursor, any MCP-compatible client |
Overview
The Model Context Protocol (MCP) is a standardized protocol that enables AI assistants and development tools to interact with your DreamFactory database services through a consistent interface. Despite the growing popularity of direct API integrations, MCP-based connections remain an essential part of modern development workflows, allowing AI assistants like ChatGPT, Claude, and Cursor to seamlessly query and manipulate your database resources.
But incorporating MCP functionality into your development environment can be challenging. Fortunately, you can use DreamFactory to easily create a full-featured MCP server that exposes your database services through the Model Context Protocol. This server can perform all of the standard database operations, including:
- Exploring database schemas, tables, and relationships
- Querying and filtering table data with advanced options
- Creating, updating, and deleting records
- Calling stored procedures and functions
- Managing database resources
In this tutorial we'll show you how to configure DreamFactory's MCP server service, and then walk through several usage examples.
Generating the MCP Server and Companion Documentation
To create an MCP Server service, log in to your DreamFactory instance using an administrator account, select the AI tab, and then click the purple plus button to create a new connection:
MCP Server Service is currently the only available selection. More AI connectors are on the way, so stay tuned for upcoming additions.
You'll be prompted to supply an API name, label, and description. Keep in mind the name must be lowercase and alphanumeric, as it will be used as the namespace within your generated API URI structure. The label and description are used for reference purposes within the administration console so you're free to title these as you please:
Next, you'll scroll down to the Advanced options section. There you'll need to supply the following details. There are only 2 required fields:
| Field | Description |
|---|---|
| API Name | Select the DreamFactory database service that you want to expose through MCP. This must be an existing database service configured in your DreamFactory instance. The dropdown will show all available database services. |
| OAuth Client ID | The OAuth Client ID is generated by Dreamfactory for you. This is the field that MCP Server users are going to provide to MCP client during connection creation. |
| OAuth Client Secret | The OAuth Client Secret is also generated by Dreamfactory for you. This is the field that MCP Server users are going to provide to MCP client during connection creation. |
| Custom Login URL | Optional Field that you could use in order to have a custom MCP login page. DreamFactory's login page would be used if nothing is provided in this field. How to configure? |
The API Name field is a dropdown that lists all available database services in your DreamFactory instance. Simply select the database service you want to expose through MCP. This service must already be configured in DreamFactory before you can select it.
After saving your changes, head over to the API Docs tab to review the generated documentation. You'll be presented with information about the MCP endpoint by running the GET request:
The mcp_endpoint field is what you should use for your AI Agents:
Example Of Usage
First of all you should get your mcp_endpoint that we will use in our Agent.
ChatGPT
To connect your MCP server with ChatGPT:
- Make sure Developer Mode is enabled in ChatGPT.
- Create a new application by navigating to: Settings -> Apps -> Advanced Settings -> Create app
- Set authentication to OAuth, use mcp_endpoint, OAuth Client ID, and OAuth Client Secret in your Agent configuration.
After creating the application, you can attach it to your chat and use its tools. For example, to show the database tables: 1. Attach your newly created application to the chat.
2. Use the Agent commands to query the MCP server. For example:
Show me tables in my database/list tables
The Agent will connect to the MCP server using the mcp_endpoint and return the available database tables, allowing you to interact with your data directly from ChatGPT.