Integrate Dify with Live JSON Data via CData Connect AI

Dify is an open source platform for building production-ready agentic workflows, chatbots, and other LLM applications. It includes built-in, two-way support for the model context protocol (MCP), allowing you to register remote MCP servers as tools in the platform to add external data sources and give your agents access to live data.

By integrating Dify with CData Connect AI through the built-in MCP Server, Dify gains governed, real-time access to live JSON services. You can list catalogs, explore schemas, and query records from JSON services using natural language prompts, with all data access running securely against authorized sources.

This article explains how to configure JSON connectivity in Connect AI, generate the required personal access token, register the Connect AI MCP Server as a tool in Dify, add it to an agent application, and verify the integration by querying live JSON services from Dify.

Step 1: Configure JSON connectivity for Dify

Connectivity to JSON from Dify is made possible through Connect AI's Remote MCP Server. To interact with JSON services from Dify, start by creating and configuring a JSON connection in Connect AI.

1. Log into Connect AI, click Sources, and then click Add Connection

2. Select JSON from the Add Connection panel

3. Enter the necessary authentication properties to connect to JSON.

   See the Getting Started chapter in the data provider documentation to authenticate to your data source: The data provider models JSON APIs as bidirectional database tables and JSON files as read-only views (local files, files stored on popular cloud services, and FTP servers). The major authentication schemes are supported, including HTTP Basic, Digest, NTLM, OAuth, and FTP. See the Getting Started chapter in the data provider documentation for authentication guides.

   After setting the URI and providing any authentication values, set DataModel to more closely match the data representation to the structure of your data.

   The DataModel property is the controlling property over how your data is represented into tables and toggles the following basic configurations.

   • Document (default): Model a top-level, document view of your JSON data. The data provider returns nested elements as aggregates of data.
   • FlattenedDocuments: Implicitly join nested documents and their parents into a single table.
   • Relational: Return individual, related tables from hierarchical data. The tables contain a primary key and a foreign key that links to the parent document.

   See the Modeling JSON Data chapter for more information on configuring the relational representation. You will also find the sample data used in the following examples. The data includes entries for people, the cars they own, and various maintenance services performed on those cars.

   
4. Click Save & Test
5. Navigate to the Permissions tab and update user-based permissions

Add a Personal Access Token

A Personal Access Token (PAT) is used to authenticate the connection to Connect AI from Dify. It is best practice to create a separate PAT for each integration to maintain granular access control.

1. Click the gear icon () at the top right of the Connect AI app to open Settings
2. On the Settings page, go to the Access Tokens section and click Create PAT
3. Give the PAT a descriptive name and click Create

4. Copy the token when displayed and store it securely. It will not be shown again

With the JSON connection configured and a PAT generated, Dify can now connect to JSON services through Connect AI.

Step 2: Register the Connect AI MCP Server in Dify

Next, register the Connect AI Remote MCP Server as a tool in Dify so your agents and workflows can discover and call live data tools through Connect AI.

1. Log into Dify, or open your self-hosted Dify instance (version 1.6.0 or later, which includes built-in MCP support)
2. Navigate to the Integrations page, select Tools and click MCP tab

3. Click Add MCP Server (HTTP) and enter the following details:
   • Server URL: https://mcp.cloud.cdata.com/mcp
   • Name Icon: Give a descriptive name, for example, CData Connect AI
   • Server Identifier: A unique identifier, for example, cdata-connect-ai
   • Headers: Add an Authorization header with the value Basic your_base64_encoded_email_PAT

   Note: Dify will use Basic authentication with Connect AI. Combine your Connect AI user email and the PAT you created earlier in the format email:PAT, base64 encode the combined string, and prefix it with Basic.

4. Click Add & Authorize. Dify connects to the Connect AI MCP Server and lists the available tools

With the MCP server registered, the Connect AI tools are available to any agent application or workflow in your Dify workspace.

Step 3: Query live JSON services from Dify

With the integration complete, build an agent application in Dify and interact with live JSON services through natural language prompts.

1. From the Dify Studio page, click Create from Blank and select Agent as the application type
2. In the agent configuration, click Add under the Tools section and select the Connect AI MCP tools registered in Step 2
3. Select an LLM provider and model for the agent so it can interpret prompts and call MCP tools
4. In the preview panel, type a prompt in the chat input, for example:
   • Use the cdata-connect-ai tools to list all available catalogs
   • Show the available schemas and tables for JSON
   • Query the top 5 records from a table in JSON
5. The Dify agent calls the Connect AI MCP Server and returns live results from JSON services

At this point, Dify communicates with the Connect AI MCP Server and retrieves live JSON services through remote MCP tools directly from your agentic workflows.

Get started with CData Connect AI

To access hundreds of SaaS, big data, and NoSQL sources directly from your cloud applications, try CData Connect AI today. Download a free 14-day trial of CData Connect AI, and our Support Team is available to help with any questions you have.