Dataiku MCP

🚀 Dataiku MCP Server

An MCP server for Dataiku DSS REST APIs, focusing on flow analysis and reliable daily operations, covering projects, datasets, recipes, jobs, scenarios, folders, variables, connections, and code environments.

⚠️ Important Note

The one-click install via Cursor includes placeholder environment values. Update DATAIKU_URL, DATAIKU_API_KEY, and optionally DATAIKU_PROJECT_KEY after adding the server.

✨ Features

• Deterministic Normalized Flow Maps: Get project.map with recipe subtypes and connectivity.
• Summary-First Outputs: Enjoy outputs with explicit raw/detail toggles where necessary.
• Broad Test Coverage: Benefit from unit, live integration, and optional destructive integration tests.
• Strong Error Taxonomy: Responses include error types like not_found, forbidden, validation, transient, unknown with retry hints.

📦 Tool Coverage

📦 Prerequisites

• Node.js 20+
• npm
• Dataiku DSS URL + API key

🚀 Quick Start

Build the Project

npm ci
npm run build

Run as a Local CLI

node dist/index.js

Use Directly from npm

npx -y dataiku-mcp

💻 Local Build And Testing

Recommended Local Workflow

# Install dependencies
npm ci

# Static checks
npm run check

# Unit tests
npm test

# Build distribution
npm run build

# Run MCP server locally (dev)
npm start

Optional Live DSS Integration Tests

# Requires DATAIKU_URL, DATAIKU_API_KEY, DATAIKU_PROJECT_KEY in .env
npm run test:integration

# Includes destructive actions (create/update/delete)
DATAIKU_MCP_DESTRUCTIVE_TESTS=1 npm run test:integration

📚 Repository Layout

• src/: Contains MCP server and tool implementations.
• tests/: Holds unit and integration test suites.
• examples/: Stores demos, fixtures, artifacts, and ad-hoc local scripts.
• bin/: Package executable entrypoint.
• dist/: Compiled output (generated).

Create a Local Env File

cp .env.example .env
# Then edit .env

Run Directly in Dev

npm start

🔧 Environment Variables

📚 MCP Client Setup Guide

General Setup

{
  "command": "npx",
  "args": ["-y", "dataiku-mcp"],
  "env": {
    "DATAIKU_URL": "https://your-dss-instance.app.dataiku.io",
    "DATAIKU_API_KEY": "your_api_key",
    "DATAIKU_PROJECT_KEY": "YOUR_PROJECT_KEY"
  }
}

Windows Note

{
  "command": "npx.cmd",
  "args": ["-y", "dataiku-mcp"],
  "env": {
    "DATAIKU_URL": "https://your-dss-instance.app.dataiku.io",
    "DATAIKU_API_KEY": "your_api_key",
    "DATAIKU_PROJECT_KEY": "YOUR_PROJECT_KEY"
  }
}

Development with TypeScript

{
  "command": "npx",
  "args": ["tsx", "/absolute/path/to/Dataiku_MCP/src/index.ts"],
  "env": {
    "DATAIKU_URL": "https://your-dss-instance.app.dataiku.io",
    "DATAIKU_API_KEY": "your_api_key",
    "DATAIKU_PROJECT_KEY": "YOUR_PROJECT_KEY"
  }
}

Claude Desktop

1. Open Claude Desktop -> Settings -> Developer -> Edit Config.
2. Add the following under mcpServers in claude_desktop_config.json:

{
  "mcpServers": {
    "dataiku": {
      "command": "npx",
      "args": ["-y", "dataiku-mcp"],
      "env": {
        "DATAIKU_URL": "https://your-dss-instance.app.dataiku.io",
        "DATAIKU_API_KEY": "your_api_key",
        "DATAIKU_PROJECT_KEY": "YOUR_PROJECT_KEY"
      }
    }
  }
}

Cursor

Cursor supports both project-scoped and global MCP config:

• Project: .cursor/mcp.json
• Global: ~/.cursor/mcp.json

Example:

{
  "mcpServers": {
    "dataiku": {
      "command": "npx",
      "args": ["-y", "dataiku-mcp"],
      "env": {
        "DATAIKU_URL": "https://your-dss-instance.app.dataiku.io",
        "DATAIKU_API_KEY": "your_api_key",
        "DATAIKU_PROJECT_KEY": "YOUR_PROJECT_KEY"
      }
    }
  }
}

Cline (VS Code extension)

1. Open Cline -> MCP Servers -> Configure MCP Servers.
2. Add the following server block in cline_mcp_settings.json:

{
  "mcpServers": {
    "dataiku": {
      "command": "npx",
      "args": ["-y", "dataiku-mcp"],
      "env": {
        "DATAIKU_URL": "https://your-dss-instance.app.dataiku.io",
        "DATAIKU_API_KEY": "your_api_key",
        "DATAIKU_PROJECT_KEY": "YOUR_PROJECT_KEY"
      }
    }
  }
}

Codex / project-level MCP config

This repo already includes a project-scoped MCP file at .mcp.json. The checked-in .mcp.json uses node node_modules/tsx/dist/cli.mjs src/index.ts for cross-platform startup (including Windows); run npm ci first.

📚 NPM Release Workflow

This repo includes a manual GitHub Actions release workflow:

• Workflow file: .github/workflows/release.yml
• Trigger: Actions -> Release NPM Package -> Run workflow

Inputs

• bump: patch | minor | major
• version: Optional exact version (overrides bump)
• publish: Whether to publish to npm

Required Repository Configuration

• GitHub variable: NPM_RELEASE_ENABLED=true
• Optional variable: NPM_PUBLISH_ACCESS=public
• Trusted publisher configured on npmjs.com for this package/repo/workflow

Workflow Steps

1. Install dependencies, run checks/tests, and build.
2. Bump package version and create git tag.
3. Push commit + tag to main.
4. Publish to npm with GitHub OIDC trusted publishing (if publish=true).
5. Create a GitHub Release with generated notes.

Trusted Publishing Setup (npm)

1. Open https://www.npmjs.com/package/dataiku-mcp -> Settings -> Trusted Publisher.
2. Choose GitHub Actions.
3. Set:
   • Organization or user: clssck
   • Repository: Dataiku_MCP
   • Workflow filename: release.yml
4. Save.

📚 Official MCP Registry

This repo is configured for MCP Registry publishing:

• Metadata file: server.json
• Workflow: .github/workflows/publish-mcp-registry.yml
• Required package field: mcpName in package.json

Server Namespace

• io.github.clssck/dataiku-mcp

Publish Paths

1. Manual: Run Publish to MCP Registry in GitHub Actions.
2. Automatic: Run the npm release workflow with publish=true (it triggers MCP Registry publish).

Validation Notes

• server.json.name must match package.json.mcpName.
• server.json.packages[].identifier + version must reference a real npm publish.

💡 Recommended Verification Prompt

After adding the server in a client, run:

• project with { "action": "map", "projectKey": "YOUR_PROJECT_KEY" } (defaults to maxNodes=300, maxEdges=600; override as needed)

You should receive a flow summary in text and normalized nodes, edges, stats, roots, and leaves under structuredContent.map. When truncation limits are applied (default maxNodes=300, maxEdges=600), structuredContent.truncation reports before/after node+edge counts and whether truncation occurred.

📄 Notes

• project.map returns a compact text summary; full normalized graph is in structuredContent.map.
• Arrays in normalized map output are deterministically sorted to reduce diff churn.
• job.wait and job.buildAndWait include structuredContent.normalizedState with one of terminalSuccess | terminalFailure | timeout | nonTerminal while preserving raw DSS state.
• With DATAIKU_DEBUG_LATENCY=1, responses include per-tool and per-API-call latency metrics under structuredContent.debug.latency.
• List-style responses are token-bounded by default; use limit/offset (and action-specific caps like maxNodes, maxEdges, maxKeys, maxPackages) to page or expand results when needed.
• dataset.get and job.get are summary-first by default; pass includeDefinition=true to include full DSS JSON in structuredContent.definition.

📚 Sources

• MCP local server connection docs: https://modelcontextprotocol.io/docs/develop/connect-local-servers
• Cursor MCP docs: https://cursor.com/docs/context/mcp
• Cline MCP docs: https://docs.cline.bot/mcp/configuring-mcp-servers