The MCP server for Dataiku DSS provides REST APIs focused on flow analysis and managing various Dataiku components such as projects, datasets, and jobs.
From the registry: MCP server for Dataiku DSS project, flow, and operations APIs.
Please install the `dataiku-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js 20+** — Install Node.js 20 or later. (https://nodejs.org)
- **Dataiku DSS API key** — Create a Dataiku DSS API key for your user account.
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","dataiku-mcp"]
- required environment variables:
- `DATAIKU_URL`: Dataiku DSS base URL (example: `https://your-dss-instance.app.dataiku.io`)
- `DATAIKU_API_KEY`: Dataiku DSS API key (example: `<your_api_key>`)
- optional environment variables:
- `DATAIKU_PROJECT_KEY`: Default project key (example: `YOUR_PROJECT_KEY`)
- `DATAIKU_REQUEST_TIMEOUT_MS`: Per-attempt request timeout in ms (example: `30000`)
- `DATAIKU_RETRY_MAX_ATTEMPTS`: Max retry attempts for GET requests (example: `4`)
- `DATAIKU_DEBUG_LATENCY`: Include per-tool timing diagnostics (example: `1`)
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.DATAIKU_URLrequiredDSS base URLDATAIKU_API_KEYrequiredDSS API key