Integrate Cursor with Live Elasticsearch Data via CData Connect AI

Yazhini G
Technical Marketing Engineer

Leverage the CData Connect AI Remote MCP Server to enable Cursor to securely access and act on live Elasticsearch data from within the editor.

Cursor is an AI-powered code editor that embeds conversational and agent-style assistance alongside your development workflow. By extending Cursor with MCP (Model Context Protocol) tools, you can give its AI agents secure access to external systems such as APIs and databases.

Integrating Cursor with CData Connect AI via the built-in CData MCP Server allows the editor's AI to query, analyze, and act on live Elasticsearch data without copying data into the IDE. The result is a development experience where you can chat with your governed enterprise data directly from Cursor.

This article outlines how to configure Elasticsearch connectivity in Connect AI, generate the required access token, register the CData MCP Server in Cursor, and then use the AI chat pane to explore live Elasticsearch data.

About Elasticsearch Data Integration

Accessing and integrating live data from Elasticsearch has never been easier with CData. Customers rely on CData connectivity to:

Access both the SQL endpoints and REST endpoints, optimizing connectivity and offering more options when it comes to reading and writing Elasticsearch data.
Connect to virtually every Elasticsearch instance starting with v2.2 and Open Source Elasticsearch subscriptions.
Always receive a relevance score for the query results without explicitly requiring the SCORE() function, simplifying access from 3rd party tools and easily seeing how the query results rank in text relevance.
Search through multiple indices, relying on Elasticsearch to manage and process the query and results instead of the client machine.

Users frequently integrate Elasticsearch data with analytics tools such as Crystal Reports, Power BI, and Excel, and leverage our tools to enable a single, federated access layer to all of their data sources, including Elasticsearch.

For more information on CData's Elasticsearch solutions, check out our Knowledge Base article: CData Elasticsearch Driver Features & Differentiators.

Getting Started

Step 1: Configure Elasticsearch connectivity for Cursor

Connectivity to Elasticsearch from Cursor is made possible through CData Connect AI's Remote MCP Server. To interact with Elasticsearch data from Cursor, start by creating and configuring a Elasticsearch connection in CData Connect AI.

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

Select Elasticsearch from the Add Connection panel

Enter the necessary authentication properties to connect to Elasticsearch.
Set the Server and Port connection properties to connect. To authenticate, set the User and Password properties, PKI (public key infrastructure) properties, or both. To use PKI, set the SSLClientCert, SSLClientCertType, SSLClientCertSubject, and SSLClientCertPassword properties.

The data provider uses X-Pack Security for TLS/SSL and authentication. To connect over TLS/SSL, prefix the Server value with 'https://'. Note: TLS/SSL and client authentication must be enabled on X-Pack to use PKI.

Once the data provider is connected, X-Pack will then perform user authentication and grant role permissions based on the realms you have configured.
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 Cursor. 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

The personal access token is only visible at creation, so be sure to copy it and store it securely for future use

With the Elasticsearch connection configured and a PAT generated, Cursor can now connect to Elasticsearch data through the CData MCP Server.

Step 2: Configure the CData MCP Server in Cursor

Next, configure Cursor to use the CData MCP Server. Cursor reads MCP configuration from an mcp.json file in the user configuration directory and exposes the registered servers under the Tools & MCP settings. Once configured, Cursor's AI chat can call the tools exposed by CData Connect AI.

Download the Cursor desktop application and complete the sign-up flow for your account
From the top menu, click Settings to open the settings panel
In the left navigation, open the Tools & MCP tab and click Add Custom MCP
Cursor opens an mcp.json file in the editor

Add the following configuration. Make sure to base64-encode your email:PAT before inserting into the header:

{
  "mcpServers": {
    "cdata-mcp": {
      "url": "https://mcp.cloud.cdata.com/mcp",
      "headers": {
        "Authorization": "Basic your_base64_encoded_email_PAT"
      }
    }
  }
}

Configuring mcp.json with CData MCP Server

Save the file
Return to Settings and then select Tools & MCP. You can now see cdata-mcp enabled with an active indicator

Step 3: Chat with CData Connect AI from Cursor

From the top bar, click Toggle AI Pane to open the chat window
Test the connection by entering "List connections"
You can also run queries like "Query Elasticsearch data and list the high priority accounts"