Model Context Protocol
Point your assistant
at your warehouse.
Ask Claude or ChatGPT about your business and get the answer from your own data. Add Dataki as a connector, sign in once, and your assistant queries the sources you have connected, saves dashboards and publishes embeds as you. It never sees a database credential.
https://dataki.ai/api/mcp Nothing to install · no API key to paste · your permissions and spend limits apply · every query logged.
01 Connecting
Add the connector. Sign in. Ask.
Claude and ChatGPT need only the endpoint. They sign you in to Dataki, where you approve what they may do and can change it any time.
-
01
Add a connector in your assistant and give it this URL.
https://dataki.ai/api/mcpIn Claude: Add custom connector.
-
02
Sign in when it asks, and approve what it may reach.
Your assistant gets its own credential, revocable at any time. No config files.
-
03
Ask a question.
No data connected yet? It hands you a link to connect a source, which takes about a minute, and carries on from there.
Step by step, for the assistant you use:
Under the hood that is OAuth 2.1 with PKCE and dynamic client registration: the client discovers where to send you, you sign in and approve the scopes, and it gets its own revocable credential tied to your account. The server acts only as you: it reaches exactly what you can reach.
Using a client that reads a config file?
Claude Code, Cursor and VS Code read the same endpoint from a file. Create an API key, on any plan, under API keys in the app's account menu and paste one of these.
{
"mcpServers": {
"dataki": {
"type": "http",
"url": "https://dataki.ai/api/mcp",
"headers": {
"Authorization": "Bearer YOUR_DATAKI_API_KEY"
}
}
}
} {
"servers": {
"dataki": {
"type": "http",
"url": "https://dataki.ai/api/mcp",
"headers": {
"Authorization": "Bearer ${input:dataki_key}"
}
}
}
} 02 In the conversation
The answer arrives as a chart you can keep.
In Claude, and in any host that draws MCP Apps, Dataki answers with a live view beside the chat: charts, tables and headline numbers exactly as they appear on a Dataki dashboard. Other hosts get the same answer as text.
- Drawn from the warehouse
- Each chart carries its query and Dataki runs it, so every figure comes straight from your warehouse.
- Checked before you see it
- Dataki checks every chart against its data before you see it, and tells the assistant exactly what to fix.
- One click to a dashboard
- Add to dashboard saves the chart as a live Dataki widget, on a new dashboard or one you already have.
How has revenue moved this year, and which categories carry it?
Dataki in Claude, on Google's public e-commerce sample dataset.
03 Tools
37 tools, in the order you would use them.
An assistant finds the sources, reads what the columns mean, then queries. The rest turn answers into dashboards, embeds and alerts your team keeps.
-
list_sourcesList data sourcesStart here — the ids every other tool expects.
-
get_data_contextRead a source's tables and what they meanTables, columns and types, with metric definitions, joins and column warnings.
-
record_data_contextWrite back what it learnedSo the next session starts where this one ended.
-
queryRun a queryRead-only SQL across one or more sources, within your spend limits, with a chart and table in hosts that show views.
-
render_uiShow something in the conversationCharts, tables and scorecards from live queries, checked before you see them.
-
refresh_viewRun a view againNew dates or filters on a chart already in the conversation.
-
save_dashboardSave a dashboardTurn an answer into a live dashboard with its own link.
-
save_widgetAdd a widgetPut one chart on a board that already exists.
-
update_widgetChange a widgetFix a chart's query, title or look where it is.
-
remove_widgetRemove a widgetTake one off a board.
-
list_dashboardsList dashboardsThe boards you can add to.
-
add_to_dashboardChoose a dashboardPick the board a chart goes on, from the conversation.
-
get_dashboardRead a dashboardWhat is on a board right now.
-
update_dashboardUpdate a dashboardIts title, theme, pages or who can see it.
-
delete_dashboardDelete a dashboardYours, when it is done.
-
publish_embedPublish an embedA public link, and the snippet to put it in a page.
-
watch_metricWatch a metricAn email when a number crosses the line you set.
-
list_schedulesList watchesEvery metric you are watching.
-
delete_scheduleStop a watchTurn off a watch you no longer need.
-
upload_fileAdd a file as a data sourceA CSV or Excel export, queried and charted like any other source.
-
replace_fileReplace a file's contentsToday's export in, the same table names kept: every dashboard on it shows the new rows.
-
create_file_uploadUpload a large fileA signed URL for a file too big to send in the call.
-
list_bigquery_projectsList Google Cloud projectsThe projects your Google account can connect, the ones with BigQuery data first.
-
connect_bigquery_projectConnect BigQueryAdd a project's datasets to your team, through a read-only service account.
-
connect_databaseConnect a databasePostgreSQL, MySQL or Redshift, tested before it is saved; the password stays encrypted in Dataki.
-
connect_google_sheetConnect a Google SheetA sheet's tabs as tables, from its link.
-
manage_sourceLook after a sourceChange a database's settings, remove a source, or put back an earlier version of a file.
-
edit_data_contextDraft, trace or remove definitionsDrafts from your tables, checked against the data; who changed each definition and when.
-
generate_dashboardHave Dataki build a dashboardA whole board planned and built from your data in a minute or two.
-
share_dashboardShare or copy a dashboardGive people or teams access, take it away, or make your own copy.
-
list_teamsList teams and their peopleWho is in each team, their roles and the invitations waiting.
-
manage_teamRun a teamCreate, rename, leave or delete one; answer an invitation.
-
manage_team_membersManage a team's peopleInvite, remove, change roles, hand the team over.
-
team_usageSee or cap a team's usageThis month's messages against the allowance, and the budget cap.
-
manage_organizationRun an organizationIts teams, people, budget and company sign-in.
-
manage_api_keysManage keys and embed appsNarrower, shorter-lived keys only: never more than this connection holds.
-
account_accessCheck your accessYour plan or trial, and which team pays.
04 Verifying
Check it from a terminal first.
Open a session yourself before you add it to an assistant. A valid key answers with the server's name and what it offers. A request with no key gets a 401 that points your client to sign-in.
More about the AI assistantcurl -sX POST https://dataki.ai/api/mcp \
-H "Authorization: Bearer YOUR_DATAKI_API_KEY" \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"curl","version":"1"}}}' SELECT plan, SUM(mrr) AS mrr
FROM billing.subscriptions
WHERE status = 'active'
GROUP BY plan
ORDER BY mrr DESC Your first month is free.
Connect a source, add the connector, and ask your first question.