Dataiku MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 34 installs a week from npm. Last commit 1 Jul 2026.
MCP server for Dataiku DSS project, flow, and operations APIs.
Today is the operative word: we check Dataiku MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add dataiku-mcp -- npx -y dataiku-mcp
{
"mcpServers": {
"dataiku-mcp": {
"args": [
"-y",
"dataiku-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.dataiku-mcp]
command = "npx"
args = ["-y", "dataiku-mcp"]
{
"mcpServers": {
"dataiku-mcp": {
"args": [
"-y",
"dataiku-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"dataiku-mcp": {
"args": [
"-y",
"dataiku-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
DATAIKU_URL (Dataiku DSS instance URL (for example, https://my-dss.app.dataiku.io).), DATAIKU_API_KEY (Dataiku API key.), DATAIKU_PROJECT_KEY (Optional default Dataiku project key.).
The author declared them in the registry entry; get the values from the project itself.
MCP server for Coolify API operations.
Python MCP server for AWS CLI inspection and operations
MCP server for local SQLite database operations
MCP server for web search operations
MCP server for Microsoft SQL Server — read and data write operations, no DDL
Official Airtable MCP server — database and operations layer for agents.
Toggl 2.0 MCP server for tasks, projects, time entries, and workspace operations.
MCP server for advanced data visualization and plotting operations
Answers built from our own checks of this server.