- Rows
- 3
- Version
- v1
- Refreshed
- 12 d ago
Import report
Nothing is changed silently. Fixes create a new version.
- All 3 rows imported. No issues found.
Cleaning rules
Rules a person approved. They run on every refresh and sync, and each change makes a new version.
AI suggestions are off for this workspace. Turning them on sends the column profile and 50 sample rows to Mistral (EU) when someone asks for suggestions. Workspace settings
Columns
Agents read what each column means and its unit. Change a type and the dataset rebuilds as a new version.| Column | Meaning | Type |
|---|---|---|
region_idunique on every row | Region identifier, unique per row iddrafted Edit | |
regionunique on every row | Region, 3 values such as Western Eu, Southern E, North Amer dimensiondrafted Edit | |
officeunique on every row | Office, 3 values such as Madrid, Paris, Toronto dimensiondrafted Edit |
Sample rows
The first 3 rows, exactly as agents receive them.
| region_id | region | office |
|---|---|---|
| EU-W | Western Europe | Paris |
| EU-S | Southern Europe | Madrid |
| NA | North America | Toronto |
Who can see this dataset
Everyone in this workspace sees it, in the app and through their agents.
Agent activity
No agent has queried this dataset in the last 30 days. Connect one below, then try one of these:
- Using datatomcp, describe the dataset regions and tell me three things worth knowing about it.
- How many rows are there per region_id in regions?
- Show me the 10 most recent rows of regions and tell me which dataset version you used.
Use it
Same engine, same numbers, whichever door you use.
- Add datatomcp from the Claude, ChatGPT or Cursor directory, or add this URL as a custom connector in any agent (Claude Code, n8n…). One connector covers all your datasets.
https://app.datatomcp.com/mcp - Sign in when asked and allow access. Then ask about regions in plain language.
Full client-by-client setup on Connect.
curl https://app.datatomcp.com/v1/datasets/ds_PefGAyGCJxxn/query \
-H "Authorization: Bearer $DATATOMCP_KEY" \
-H "Content-Type: application/json" \
-d '{"limit": 10}'Create an API key in Account. Filters, metrics and paging are in the dataset docs.
Use the datatomcp dataset "regions" (id ds_PefGAyGCJxxn) to answer questions about this data. Call describe_dataset first to read the columns and today's date. Before filtering on a text column such as region_id, call distinct_values to get the exact spelling. Use aggregate for totals, counts and averages instead of reading rows. Never sum a column marked summable: false (prices, rates). Quote numbers exactly as returned with the unit from meta.units, mention the dataset version, and pass on meta.warnings that affect the number.
Paste this into your agent's instructions so it queries this dataset the right way.