Exploratory Data Catalog

The Home for Trusted Data,
Built for Humans and AI Agents

Prepare data, add business context, share it, and see how it's used.
Updates run automatically, so your team and AI agents always work with the latest data.

Start a 30-day free trial

  • Choose where data lives: PC or server
  • Manage AI access per dataset
  • Monitor who used your data, and when

Publish, add business context, ask from an AI agent, and see every access.

AI Can Analyze Your Data.
But Can You Really Trust It?

The problem isn't the AI. It's the data you give it. Without trusted data and business context, AI misreads your data, repeats the same work, and wastes tokens.

A net sales by region chart where returned orders are counted as sales, so the West looks like the leader

Wrong answers

AI misreads your data and your business rules.

Business context in Metadata
Three people ask questions, and the same clean, join and filter steps run again for each one

Repeated work

AI cleans and prepares the same data every time someone asks.

Prepare once, with recorded steps
The AI reads 1.2 million rows when the answer needs only 6

Wasted time and tokens

AI reads far more data than the question needs.

Queries that run where the data is

Better AI answers don't start with a better prompt. They start with better-prepared, better-understood data.

Same question, two answers

Give AI the data, and the context, to get it right

"What were net sales by region in 2026?"
Without business context

The West comes out on top

The AI adds up every order. The West's 13.7% return rate inflates its sales, so it looks like the leader.

With approved business context

The Southeast comes out on top

The AI follows the approved definition, which matches how the business counts net sales.

Net sales = sum of sales where return_flag = "N"
This exampleThe query ran where the data is, and 6 rows came back instead of 23,360.

One example from the demo sales data. Business context helps AI answer more reliably; it doesn't guarantee a correct answer.

How it works

Five stages, one dataset you can trust

  1. 1Prepare
  2. 2Share
  3. 3Verify
  4. 4Add Context
  5. 5Monitor

Monitor feeds back into Add Context: what people ask tells you what context to add next.

Stage 1 · Prepare

Prepare once, keep it up to date

Clean, join and calculate with recorded steps in Exploratory.

Then schedule a refresh: Exploratory re-queries the source and reruns every step, so the data is always ready.

  • Databases
  • Cloud apps
  • R scripts generated with AI Data
  • Local files
Stage 2 · Share

Publish to Local or to Server

Publish the result to the Data Catalog: on your PC (Local), or on Exploratory Server for your team.

People and AI agents then use the same prepared data, not their own versions.

Stage 3 · Verify

Check it before you rely on it

Every dataset has the same views: Summary for each column's distribution and missing values, Table to filter and aggregate, and Wrangling Steps to see exactly how each number was made.

You don't have to take anyone's word for it.

Stage 4 · Add Context

Teach AI what your data means

In the Metadata view, Generate / improve with AI drafts the business context from the data and from the recorded wrangling steps. You review it, fix what's off, and approve it.

  1. Meaning of the data
  2. Column meanings and roles
  3. Business metrics
  4. Aggregation rules and cautions
  5. Questions and aggregation examples
Stage 5 · Monitor

See how the data is used

The Access Log shows who used the data, when, and how, and the exact query they ran.

The queries and their run times give you hints on how to improve the business context.

And if you see access you didn't expect, you can shut off a channel such as MCP or the CLI.

Security and control: your data, your rules

Share Data with AI Agents, with Confidence

Where your data lives, who can use which data, and how it was used. With the Data Catalog, you decide all of it and can check all of it.

Keep it on your PC

Publish to the Local Data Catalog and the data never goes to Exploratory Server.

Decide what AI can reach

Turn MCP and CLI access on or off for each dataset, at any time. In Exploratory Desktop, you can also turn MCP and CLI off for the whole app.

AI sees only what it should

On Server, an AI app signs in as the person, so it sees only the data that person may see. Everywhere, AI agents get only approved business context.

See every access

On the Data Catalog page, the dataset owner can see in the Access Log who used which data, when, through which channel, and the exact query. Each dataset has its own Access Log tab too.

Local or Server

Choose Where Each Dataset Lives

Data that shouldn't leave your company stays in the Local Data Catalog on your PC; data your team needs goes on the server. The main features work in both.

Local Data CatalogServer Data Catalog
Where the data livesYour PCExploratory Server
Who can use itYou, in Exploratory DesktopPeople in your organization, with their own permissions
SharingNoneTeam sharing and a web page for each dataset
Scheduled refreshYesYes
Summary, Table, Wrangling StepsYesYes
Metadata (business context)YesYes
Access LogYes: Exploratory Desktop, MCP, CLIYes, for the dataset owner: web page, MCP, CLI, API, with IP address
MCP and CLI on or off per datasetYesYes
MCP and CLI on or off for the whole appYes, in System Settings—
AI apps through MCPDesktop MCP: Claude Code, Codex, Antigravity, CursorServer MCP: Claude, ChatGPT, Microsoft Copilot, Gemini, Claude Code. The AI signs in as the user and sees only what that user may see.
Best forPersonal work, and companies whose policy keeps data off external serversShared, governed data for teams and organizational AI
Local, for privacy-first teams

Your data, your PC, your AI tools

Some companies don't allow data on external servers, or AI features inside other apps, but do allow a company-approved AI client such as Claude Code.

With the Local Data Catalog, you prepare data in Exploratory, keep it on your PC, and query it from the AI tool your company already approved. You decide which datasets that tool can reach, and the Access Log records each query.

System Settings, MCP / CLI: the MCP switch, the Exploratory Desktop plugin installer for Claude Code, Codex, Antigravity and Cursor, and the CLI switch

Turn on MCP and install the plugin for Claude Code, Codex, Antigravity or Cursor in one click. Turn the CLI on or off in the same place.

One dataset, three ways in

The same trusted data, for your team and your AI agents

sales_ordersData Catalog · 23,360 rows · Approved business context

You

From any project in Exploratory Desktop, pick a dataset from the Local or Server Data Catalog, build a query visually (select columns, filter, aggregate, join), and get the result.

Your teamServer

Import the data straight into Exploratory Desktop for analysis, or check and visualize it in a web browser and download the rows you need as a CSV to use in Excel and other tools.

AI agents

Find the dataset they need, read its approved business context, and run a query through MCP. They can reach only the data that the account they signed in with through OAuth has permission for.

Getting started

Start with a dataset you already have

  1. Prepare it

    Import a source, clean it with recorded steps, and schedule a refresh.

  2. Publish it

    • Local: on your PC, for you and your AI tools.
    • Server: for your team, with permissions.
  3. Add context and use it

    Generate and approve the business context, then query the data yourself or connect your AI app through MCP.

Watch: What Is a Data Catalog? (5 min)

FAQ

Frequently Asked Questions

What is Exploratory Data Catalog?

One place in Exploratory to prepare, verify, and share trusted data that people and AI agents can understand and query efficiently. Every dataset has the same views: Summary, Table, Wrangling Steps, Metadata and Access Log. It runs on your PC (Local) or on Exploratory Server for your team.

Do I need an AI agent to benefit from it?

No. Scheduled refresh keeps your data up to date, and Summary, Table and Wrangling Steps let you verify it. In Exploratory Desktop, you can build a query in the UI and import just the data you need into any project. AI agents are one more way to use it.

Does my data have to go to a server?

No. Publish to the Local Data Catalog and the data stays on your PC; it never goes to Exploratory Server.

Does Local mean no data reaches an AI provider?

Not by itself. The dataset stays on your PC, but the query results your AI client receives go to that AI provider, under your company's agreement with them.

You decide which datasets your AI client can reach, and the Access Log records each query.

Can I stop AI agents or the CLI from using a dataset?

Yes. Turn MCP and CLI access on or off for each dataset, at any time, on Local and on Server. In Exploratory Desktop, you can also turn MCP and CLI off for the whole app in System Settings.

How do I see who is using my data?

Open the Access Log on the Data Catalog page, or the Access Log tab of a dataset. It shows who used which data, when, through which channel, and the exact query. Only the dataset's owner sees it.

Which AI apps can connect, and how?
  • Desktop MCP (Local): Claude Code, Codex, Antigravity, Cursor and other tools you install on your computer. Turn on MCP in Exploratory's System Settings and install the plugin in one click.
  • Server MCP: Claude, Claude Code, ChatGPT, Microsoft Copilot, Gemini, Grok Bot and more. The AI app signs in as you and sees only the data you may see.
How does business context improve AI answers?

Business context tells the AI what the data means: what one row is, what each column means, how metrics are defined, and how to aggregate.

It helps AI answer more reliably; it doesn't guarantee a correct answer. AI agents get only the context you approved.

How do permissions and the Access Log work?

On Server, people use each dataset with their own permissions, and an AI app signs in as the person, so it sees only what that person may see. On both Local and Server, you can turn MCP and CLI access on or off per dataset.

The Access Log records each access. On Server: the web page, MCP, the CLI and the API, with the IP address. On Local: Exploratory Desktop, MCP and the CLI. Only the dataset's owner sees it.

Can I refresh data automatically?

Yes. Schedule a refresh: Exploratory re-queries the source and reruns every recorded step, so the dataset in the Data Catalog stays up to date, on Local and on Server.

The Home for Trusted Data,
Built for Humans and AI Agents

Prepare your data once. Give people and AI agents the context and access they need.

Enter a Note Name
Loading the Note Editor...