Integrating Cursor with Mixpanel Data via CData CLI
Cursor is an AI editor and coding agent Anysphere built to plan, write, and review code using agents that understand your entire codebase. You can access it through a desktop app or a CLI, which brings these agentic capabilities natively to the terminal, allowing developers to run agents in any terminal, script, or editor without switching context. Its support for integrations and custom agent rules makes Cursor well-suited for structured, multi-step workflows, making it a natural fit for connecting to external data sources through tools like CData CLI. By describing your data goals in plain language, Cursor's agent handles the full setup process from driver configuration to query execution without manual intervention at each step.
This article walks through how to connect Mixpanel to Cursor through CData CLI.
Prerequisites
- Cursor CLI installed
- Cursor Desktop installed
- CData CLI installed
- Access to Mixpanel
Step 1: Download the skill (one-time setup)
Always use the CData CLI with the official Skill.
-
The official CData CLI Skill on GitHub can be downloaded using npx skills through the terminal:
npx skills add CDataSoftware/cli-skills -
Follow the prompts in the terminal to install for Cursor.
Step 2: Set up the project directory
Create a project directory to contain all project files. Below are examples for using Cursor in either the Terminal or Desktop app.
Cursor in Terminal CLI
Navigate to your desired directory in the terminal and start a session with the agent command.
Cursor Desktop App
Select the working directory within the desktop app.
Step 3: Establish the driver and connection
Describe what you want to accomplish in this session with the CLI and Mixpanel data.
I would like to build a command line app that connects to Mixpanel and checks for updates from Annotations. Make sure to include data from important columns like AnnotationId and ProjectId.
This prompt automatically loads the Skill and kicks off the following process. You can also manually prompt the agent for each of the following steps.
- Driver setup: Cursor checks for an existing CData Mixpanel driver, or searches and downloads a new one:
cdatacli drivers listcdatacli drivers search --driver "Mixpanel"cdatacli drivers download --artifact-id <artifact-id>- Activation: Activate the Mixpanel driver with a single command for a trial or full license:
cdatacli drivers activate "Mixpanel" --name "<name>" --email "<email>" --trialcdatacli drivers activate "Mixpanel" --name "<name>" --email "<email>" --key "<product-key>"- Establish the connection: Check for existing Mixpanel connections or create a new one:
cdatacli connection listcdatacli connection create --driver Mixpanel --name my_mixpanel_connection --connectionstring "Prop1=value1;Prop2=value2;..."- Create a Mixpanel skill (if applicable): CData provides driver instructions for popular sources that can be used to create a source-specific skill to guide the agent through best practices for the driver.
- Run the following command to generate a skill file and save the output to your skills directory. You can choose to save the skill either at the project level or globally. (Note: If "No instructions available for Mixpanel" error is returned, no driver instructions exist and you can continue to use main driver skill)
cdatacli drivers skill "Mixpanel" > ~/skills/cdata-mixpanel/SKILL.md
Step 4: Query Mixpanel data
With the CData driver configured, your agent can execute queries and write code against live Mixpanel data:
cdatacli query sql --connection my_mixpanel_connection --sql "SELECT * FROM Annotations"
Query Mixpanel data directly from your terminal with CData
Cursor and CData CLI together give your AI coding agent a direct path to live Mixpanel data without custom middleware, scheduled syncs, or manual setup at each step. Describe your goal, and the agent handles driver configuration, connection setup, and query execution from start to finish in the terminal.
Download the free CData CLI and start a free, 30-day trial of the CData API Driver for JDBC today.