• DATA
  • STATUS
  • CONTROL
  • HUMAN

How to run SQL queries on mobility data with your AI

Connect Veraset to your AI client once. From there, your agent handles the heavy lifting of writing and executing complex SQL against Veraset's geolocation datasets.

Ask AI about this page

Short answer

How can I run SQL on Veraset mobility data using AI?

Your AI writes the SQL syntax, executes it against the Veraset datasets, and pulls the resulting aggregations directly into your chat. You get precise movement insights without manually writing queries or managing database connections. Here is how the process works.

The results you get

Query outcomes

Once your AI processes a request, you get these specific results.

DATA

Aggregated movement stats

The AI pulls specific counts, averages, or distributions from the geolocation data. You receive the summarized tables directly in your chat.

STATUS

Real-time query tracking

For large datasets, your agent monitors the progress of the execution. You'll know exactly when the data is ready or if a process is still running.

CONTROL

Query management

If a query is taking too long or you change your mind, your agent can stop the execution immediately. This prevents wasted compute.

HUMAN

Manual oversight

The AI handles the syntax, but you decide which logic to apply. You remain the final authority on the query parameters and the interpretation of the results.

The workflow

What your AI does when the request arrives.

The AI acts as the bridge between your natural language questions and the Veraset database.

  1. Translate intent to SQL

    Your agent converts your plain English questions about movement patterns into valid SQL statements compatible with Veraset's schema.

    execute_sql_query

  2. Monitor execution

    Because mobility datasets are massive, the agent tracks the status of the query to ensure it completes successfully.

    get_query_status

  3. Fetch the data

    Once the database finishes the calculation, the agent pulls the resulting rows into your conversation.

    get_query_results

  4. Manage active tasks

    If you realize a query is too broad or incorrect, the agent can kill the process to save time.

    cancel_running_query

Try it

Copy these to start.

Use these prompts to kick off your first analysis.

Starting points

These are templates. Swap out the specific locations, timeframes, or metrics to match your actual research needs.

Veraset Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_WyJVIYHTFBZLnrJEVxBMkosMzJgHAkxuEd8yrcsO/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Veraset capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "veraset-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_WyJVIYHTFBZLnrJEVxBMkosMzJgHAkxuEd8yrcsO/mcp"
    }
  }
}
Copy into chat04

  • Show me the total number of unique device IDs in Los Angeles from last Tuesday.

  • Calculate the average dwell time for visitors in the Times Square area during morning rush hour.

  • Find the top 5 most common movement corridors between Brooklyn and Manhattan for the last month.

  • Run a query to count how many devices moved from residential zones to commercial zones between 8 AM and 10 AM.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Veraset once, then ask.

One-click connection handles the setup. Your credentials stay encrypted, and you can immediately start querying Veraset data through your preferred AI client.

Connect Veraset to your AI

FAQ

How the Veraset connector behaves

  • 01

    Can my AI edit the underlying Veraset datasets?

    No. The tools only allow for reading and executing queries. The AI cannot modify, delete, or overwrite any original mobility data.

  • 02

    Does the AI write the SQL for me?

    Yes. You provide the goal in plain English, and the agent generates and runs the necessary SQL to get the answer.

  • 03

    Can I stop a query if it's taking too long?

    Yes. You can tell your agent to stop the current task, and it will use the specific tool to cancel the running query.

  • 04

    Can the AI create new tables in Veraset?

    No. The available tools are limited to executing queries and retrieving results. It cannot perform DDL operations like CREATE or DROP.

  • 05

    How do I see the results of my query?

    The agent automatically fetches the results once the query status shows it is finished, presenting them directly in your chat.

  • More questions about Veraset? See everything the Veraset Connector can do

Connect Veraset to Claude, Cursor, ChatGPT & more