![]() |
VOOZH | about |
Windsurf is an AI-native IDE built around Cascade, an autonomous coding agent that understands project context and executes multi-step tasks directly inside the editor. Cascade supports the Model Context Protocol (MCP), allowing the agent to discover and call external tools and data sources without leaving the development environment.
By integrating Windsurf with CData Connect AI through the built-in MCP server, the Cascade agent gains governed, real-time access to live FHIR data. This enables developers to list catalogs, inspect schemas, and query records from FHIR data within the IDE using natural language prompts.
This article explains how to configure FHIR connectivity in Connect AI, generate the required personal access token, configure the Connect AI MCP Server in Windsurf, and verify the integration by querying live FHIR data from the Cascade chat.
Connectivity to FHIR from Windsurf is made possible through Connect AI's Remote MCP Server. To interact with FHIR data from Windsurf, start by creating and configuring a FHIR connection in Connect AI.
Set URL to the Service Base URL of the FHIR server. This is the address where the resources are defined in the FHIR server you would like to connect to. Set ConnectionType to a supported connection type. Set ContentType to the format of your documents. Set AuthScheme based on the authentication requirements for your FHIR server.
Generic, Azure-based, AWS-based, and Google-based FHIR server implementations are supported.
The product supports connections to custom instances of FHIR. Authentication to custom FHIR servers is handled via OAuth (read more about OAuth in the Help documentation. Before you can connect to custom FHIR instances, you must set ConnectionType to Generic.
π Configuring a connection (Salesforce is shown)A Personal Access Token (PAT) is used to authenticate the connection to Connect AI from Windsurf. It is best practice to create a separate PAT for each integration to maintain granular access control.
With the FHIR connection configured and a PAT generated, Windsurf can now connect to FHIR data.
Next, configure the Connect AI Remote MCP Server in Windsurf so that the Cascade agent can discover and call live data tools through Connect AI.
{
"mcpServers": {
"cdata-mcp": {
"serverUrl": "https://mcp.cloud.cdata.com/mcp",
"headers": {
"Authorization": "Basic your_base64_encoded_email_PAT",
"Content-Type": "application/json"
}
}
}
}
Note: Windsurf 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. For example, given [email protected]:ABC123...XYZ789, the Authorization header value becomes something like: Basic dXNlckBkb21haW4uY29tOkFCQzEyMy4uLlhZWjc4OQ==
π Pasting Connect AI MCP Server configurationWith the MCP server registered and enabled, Windsurf is ready to query live FHIR data through Connect AI.
With the integration complete, use the Cascade chat panel in Windsurf to interact with live FHIR data through natural language prompts.
At this point, your Windsurf IDE communicates with the Connect AI MCP Server and retrieves live FHIR data through remote MCP directly from the editor.
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 today, and as always, our Support Team is available to assist you with any questions you may have.
Learn more about CData Connect AI or sign up for free trial access:
Free Trial