Integrate Dify with Live Odoo 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 Odoo data. You can list catalogs, explore schemas, and query records from Odoo data using natural language prompts, with all data access running securely against authorized sources.
This article explains how to configure Odoo 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 Odoo data from Dify.
About Odoo Data Integration
Accessing and integrating live data from Odoo has never been easier with CData. Customers rely on CData connectivity to:
- Access live data from both Odoo API 8.0+ and Odoo.sh Cloud ERP.
-
Extend the native Odoo features with intelligent handling of many-to-one, one-to-many, and many-to-many data properties. CData's connectivity solutions also intelligently handle complex data properties within Odoo. In addition to columns with simple values like text and dates, there are also columns that contain multiple values on each row. The driver decodes these kinds of values differently, depending upon the type of column the value comes from:
- Many-to-one columns are references to a single row within another model. Within CData solutions, many-to-one columns are represented as integers, whose value is the ID to which they refer in the other model.
- Many-to-many columns are references to many rows within another model. Within CData solutions, many-to-many columns are represented as text containing a comma-separated list of integers. Each value in that list is the ID of a row that is being referenced.
- One-to-many columns are references to many rows within another model - they are similar to many-to-many columns (comma-separated lists of integers), except that each row in the referenced model must belong to only one in the main model.
- Use SQL stored procedures to call server-side RFCs within Odoo.
Users frequently integrate Odoo with analytics tools such as Power BI and Qlik Sense, and leverage our tools to replicate Odoo data to databases or data warehouses.
Getting Started
Step 1: Configure Odoo connectivity for Dify
Connectivity to Odoo from Dify is made possible through Connect AI's Remote MCP Server. To interact with Odoo data from Dify, start by creating and configuring a Odoo connection in Connect AI.
- Log into Connect AI, click Sources, and then click Add Connection
- Select Odoo from the Add Connection panel
-
Enter the necessary authentication properties to connect to Odoo.
To connect, set the Url to a valid Odoo site, User and Password to the connection details of the user you are connecting with, and Database to the Odoo database.
- Click Save & Test
- 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.
- Click the gear icon () at the top right of the Connect AI app to open Settings
- On the Settings page, go to the Access Tokens section and click Create PAT
- Give the PAT a descriptive name and click Create
- Copy the token when displayed and store it securely. It will not be shown again
With the Odoo connection configured and a PAT generated, Dify can now connect to Odoo data 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.
- Log into Dify, or open your self-hosted Dify instance (version 1.6.0 or later, which includes built-in MCP support)
- Navigate to the Integrations page, select Tools and click MCP tab
-
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.
-
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 Odoo data from Dify
With the integration complete, build an agent application in Dify and interact with live Odoo data through natural language prompts.
-
From the Dify Studio page, click Create from Blank and select Agent as the application type
-
In the agent configuration, click Add under the Tools section and select the Connect AI MCP tools registered in Step 2
- Select an LLM provider and model for the agent so it can interpret prompts and call MCP tools
-
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 Odoo
- Query the top 5 records from a table in Odoo
-
The Dify agent calls the Connect AI MCP Server and returns live results from Odoo data
At this point, Dify communicates with the Connect AI MCP Server and retrieves live Odoo data 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.