Which integrations are available for this server?

Provides tools to manage recipes, datasets, and scenarios in Dataiku DSS, including creating, updating, deleting, running, and inspecting various objects.

How do I use Dataiku DSS MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Dataiku DSS MCP Server list datasets in project 'Sales'" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Dataiku DSS MCP Server

by steven0lisa

Overview Schema Source Related Servers Discussions Admin

JavaScript

Remote

Dataiku DSS MCP Server

A comprehensive Model Context Protocol (MCP) server for Dataiku DSS integration. This project provides Claude Code with direct access to Dataiku DSS for managing recipes, datasets, and scenarios.

🚀 Quick Start

Prerequisites

Node.js 18.0.0+
Dataiku DSS instance with API access
Valid DSS API key

Installation

# Install globally
npm install -g @zhangzichao2008/mcp-dataiku

# Or use with npx
npx @zhangzichao2008/mcp-dataiku

Configuration

Copy environment template:

cp .env.sample .env

Configure your DSS connection in .env:

DSS_HOST=https://your-dss-instance.com:10000
DSS_API_KEY=your-api-key-here
DSS_INSECURE_TLS=true  # Only if using self-signed certificates

Claude Code Integration

claude mcp add dataiku-dss \
    -e DSS_HOST=https://your-dss-instance.com:10000 \
    -e DSS_API_KEY=your-api-key-here \
    -e DSS_INSECURE_TLS=true \
    -- npx @zhangzichao2008/mcp-dataiku

Related MCP server: MCP-Server

📚 MCP Tool Catalog

Core Recipe Management Tools

Tool	Description	Key Parameters
`create_recipe`	Create new recipe	`project_key`, `recipe_type`, `recipe_name`, `inputs`, `outputs`, `code`
`update_recipe`	Update existing recipe	`project_key`, `recipe_name`, `**kwargs`
`delete_recipe`	Delete recipe	`project_key`, `recipe_name`
`run_recipe`	Execute recipe	`project_key`, `recipe_name`, `build_mode`

Core Dataset Management Tools

Tool	Description	Key Parameters
`create_dataset`	Create new dataset	`project_key`, `dataset_name`, `dataset_type`, `params`
`update_dataset`	Update dataset settings	`project_key`, `dataset_name`, `**kwargs`
`delete_dataset`	Delete dataset	`project_key`, `dataset_name`, `drop_data`
`build_dataset`	Build dataset	`project_key`, `dataset_name`, `mode`, `partition`
`inspect_dataset_schema`	Get dataset schema	`project_key`, `dataset_name`
`check_dataset_metrics`	Get dataset metrics	`project_key`, `dataset_name`

Core Scenario Management Tools

Tool	Description	Key Parameters
`create_scenario`	Create new scenario	`project_key`, `scenario_name`, `scenario_type`, `definition`
`update_scenario`	Update scenario settings	`project_key`, `scenario_id`, `**kwargs`
`delete_scenario`	Delete scenario	`project_key`, `scenario_id`
`run_scenario`	Execute scenario	`project_key`, `scenario_id`

🔧 Advanced Tools

Tool	Description	Key Parameters
`get_scenario_logs`	Get detailed run logs and error messages	`project_key`, `scenario_id`, `run_id`
`get_recipe_code`	Extract actual Python/SQL code from recipes	`project_key`, `recipe_name`
`get_project_flow`	Get complete data flow/pipeline structure	`project_key`
`get_dataset_sample`	Get sample data from datasets	`project_key`, `dataset_name`, `rows`, `columns`
`get_recent_runs`	Get recent run history across scenarios/recipes	`project_key`, `limit`, `status_filter`
`list_projects`	List all available Dataiku projects	-

Additional Dataset Tools

Tool	Description	Key Parameters
`list_datasets`	List all datasets in a project	`project_key`, `dataset_type` (optional)
`get_dataset_info`	Get detailed information about a dataset	`project_key`, `dataset_name`
`clear_dataset`	Clear data from a dataset	`project_key`, `dataset_name`, `partition` (optional)

Additional Recipe Tools

Tool	Description	Key Parameters
`list_recipes`	List all recipes in a project	`project_key`, `recipe_type` (optional)
`get_recipe_info`	Get detailed information about a recipe	`project_key`, `recipe_name`
`validate_recipe_syntax`	Validate Python/SQL syntax of a recipe	`project_key`, `recipe_name`, `code` (optional)
`test_recipe_dry_run`	Test recipe logic without actual execution	`project_key`, `recipe_name`, `sample_rows`

Additional Scenario Tools

Tool	Description	Key Parameters
`list_scenarios`	List all scenarios in a project	`project_key`, `scenario_type`, `active_only`
`get_scenario_info`	Get detailed information about a scenario	`project_key`, `scenario_id`
`add_scenario_trigger`	Add a trigger to a scenario	`project_key`, `scenario_id`, `trigger_type`, trigger params
`remove_scenario_trigger`	Remove a trigger from a scenario	`project_key`, `scenario_id`, `trigger_idx`
`get_scenario_run_history`	Get run history for a scenario	`project_key`, `scenario_id`, `limit`
`get_scenario_steps`	Get step configuration including Python code	`project_key`, `scenario_id`
`clone_scenario`	Clone an existing scenario with modifications	`project_key`, `source_scenario_id`, `new_scenario_name`, `modifications`

Advanced Tools

Tool	Description	Key Parameters
`search_project_objects`	Search for datasets, recipes, scenarios by name/pattern	`project_key`, `search_term`, `object_types`
`get_code_environments`	List available Python/R environments	`project_key` (optional)
`get_project_variables`	Get project-level variables and configuration	`project_key`
`get_connections`	List available data connections	`project_key` (optional)
`get_job_details`	Get detailed job execution information	`project_key`, `job_id`
`cancel_running_jobs`	Cancel running jobs/scenarios	`project_key`, `job_ids`
`batch_update_objects`	Update multiple objects with similar changes	`project_key`, `object_type`, `pattern`, `updates`
`get_project_flow`	Get complete data flow/pipeline structure	`project_key`
`export_project_config`	Export project configuration as JSON/YAML	`project_key`, `format`
`duplicate_project_structure`	Copy project structure to new project	`source_project_key`, `target_project_key`, `include_data`

Total: 46 Tools

🔧 Usage Examples

Core Operations

Creating a Python Recipe

{
  "project_key": "ANALYTICS_PROJECT",
  "recipe_type": "python",
  "recipe_name": "data_cleaner",
  "inputs": ["raw_data"],
  "outputs": [{"name": "clean_data", "new": true, "connection": "filesystem_managed"}],
  "code": "import pandas as pd\ndf = dataiku.Dataset(\"raw_data\").get_dataframe()\ndf_clean = df.dropna()\ndataiku.Dataset(\"clean_data\").write_with_schema(df_clean)"
}

Building a Dataset

{
  "project_key": "BI",
  "dataset_name": "user_analytics",
  "mode": "RECURSIVE_BUILD"
}

Getting Dataset Sample

{
  "project_key": "FINANCE_PROJECT",
  "dataset_name": "transactions",
  "rows": 500,
  "columns": ["customer_id", "amount"]
}

Getting Scenario Logs

{
  "project_key": "ANALYTICS_PROJECT",
  "scenario_id": "data_processing"
}

Exploring Project Structure

{
  "project_key": "SALES_ANALYTICS"
}

🏗️ Architecture

mcp-dataiku/
├── src/
│   ├── dataiku-client.ts   # Dataiku API client
│   └── mcp-server.ts       # MCP server implementation
├── package.json
├── tsconfig.json
├── .env.sample
└── README.md

🔒 Security

API Key Protection: Store API keys in environment variables, never in code
SSL Configuration: Support for self-signed certificates with DSS_INSECURE_TLS=true
Permission Validation: All operations respect DSS user permissions
Error Handling: Sensitive information is not exposed in error messages

📈 Monitoring

The MCP server provides logging for monitoring:

# Check logs for debugging
tail -f dataiku_mcp.log

🤝 Contributing

Fork the repository
Create a feature branch: git checkout -b feature/amazing-feature
Commit changes: git commit -m 'Add amazing feature'
Push to branch: git push origin feature/amazing-feature
Open a Pull Request

Development Setup

# Install dependencies
npm install

# Run in development mode
npm run dev

# Build for production
npm run build

# Run basic validation tests (no actual API calls)
npm test

# Run comprehensive tests (requires Dataiku DSS)
node test-comprehensive.js

# Clean build artifacts
npm run clean

# Publish new version (patch version)
npm run publish:patch

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🔗 Links

📞 Support

If you encounter any issues or have questions, please open an issue on GitHub.

Ready to enhance your Dataiku workflows with AI assistance! 🚀

Available Tools

43 tools

add_scenario_triggerB

Add a trigger to a scenario

Inputs: project_key (required), scenario_id (required), trigger_type (required), every_minutes, +4 more.

batch_update_objectsC

Update multiple objects with similar changes

Inputs: project_key (required), object_type (required), pattern (required), updates (required).

build_datasetC

Build a dataset

Inputs: project_key (required), dataset_name (required), mode, partition.

cancel_running_jobsC

Cancel running jobs/scenarios

Inputs: project_key (required), job_ids (required).

check_dataset_metricsB

Get latest dataset metrics

Inputs: project_key (required), dataset_name (required).

clear_datasetC

Clear data from a dataset

Inputs: project_key (required), dataset_name (required), partition.

clone_scenarioB

Clone an existing scenario with modifications

Inputs: project_key (required), source_scenario_id (required), new_scenario_name (required), modifications.

create_datasetC

Create a new dataset in a project

Inputs: project_key (required), dataset_name (required), dataset_type (required), params (required).

create_recipeB

Create a new recipe in a Dataiku project

Inputs: project_key (required), recipe_type (required), recipe_name (required), inputs (required), +2 more.

create_scenarioB

Create a new scenario in a project

Inputs: project_key (required), scenario_name (required), scenario_type (required), definition.

delete_datasetC

Delete a dataset from a project

Inputs: project_key (required), dataset_name (required), drop_data.

delete_recipeB

Delete a recipe from a project

Inputs: project_key (required), recipe_name (required).

delete_scenarioB

Delete a scenario from a project

Inputs: project_key (required), scenario_id (required).

duplicate_project_structureC

Copy project structure to new project

Inputs: source_project_key (required), target_project_key (required), include_data.

export_project_configC

Export project configuration as JSON/YAML

Inputs: project_key (required), format.

get_code_environmentsB

List available Python/R environments

Inputs: project_key.

get_connectionsC

List available data connections

Inputs: project_key.

get_dataset_infoC

Get detailed information about a dataset

Inputs: project_key (required), dataset_name (required).

get_dataset_sampleC

Get sample data from datasets

Inputs: project_key (required), dataset_name (required), rows, columns.

get_job_detailsC

Get detailed job execution information

Inputs: project_key (required), job_id (required).

get_project_flowB

Get complete data flow/pipeline structure

Inputs: project_key (required).

get_project_variablesC

Get project-level variables and configuration

Inputs: project_key (required).

get_recent_runsB

Get recent run history across all scenarios/recipes

Inputs: project_key (required), limit, status_filter.

get_recipe_codeB

Extract actual Python/SQL code from recipes

Inputs: project_key (required), recipe_name (required).

get_recipe_infoB

Get detailed information about a recipe

Inputs: project_key (required), recipe_name (required).

get_scenario_infoC

Get detailed information about a scenario

Inputs: project_key (required), scenario_id (required).

get_scenario_logsB

Get detailed run logs and error messages for failed scenarios

Inputs: project_key (required), scenario_id (required), run_id.

get_scenario_run_historyB

Get run history for a scenario

Inputs: project_key (required), scenario_id (required), limit.

get_scenario_stepsB

Get step configuration including Python code

Inputs: project_key (required), scenario_id (required).

inspect_dataset_schemaC

Get dataset schema information

Inputs: project_key (required), dataset_name (required).

list_datasetsA

List all datasets in a project

Inputs: project_key (required), dataset_type, search, simple.

list_projectsB

List all available Dataiku projects

Inputs: no named parameters.

list_recipesC

List all recipes in a project

Inputs: project_key (required), recipe_type, search, simple.

list_scenariosC

List all scenarios in a project

Inputs: project_key (required), scenario_type, active_only.

remove_scenario_triggerB

Remove a trigger from a scenario

Inputs: project_key (required), scenario_id (required), trigger_idx (required).

run_recipeC

Run a recipe to build its outputs

Inputs: project_key (required), recipe_name (required), build_mode.

run_scenarioC

Run a scenario manually

Inputs: project_key (required), scenario_id (required).

search_project_objectsB

Search for datasets, recipes, scenarios by name/pattern

Inputs: project_key (required), search_term (required), object_types.

test_recipe_dry_runB

Test recipe logic without actual execution

Inputs: project_key (required), recipe_name (required), sample_rows.

update_datasetC

Update dataset settings

Inputs: project_key (required), dataset_name (required).

update_recipeC

Update an existing recipe

Inputs: project_key (required), recipe_name (required).

update_scenarioC

Update scenario settings

Inputs: project_key (required), scenario_id (required).

validate_recipe_syntaxB

Validate Python/SQL syntax of a recipe

Inputs: project_key (required), recipe_name (required), code.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3/5.0

Scored 2026-06-10 04:50 across 43 tools

Disambiguation4/5

Most tools have distinct purposes, e.g., get_recipe_info vs get_recipe_code clearly separate; overlapping functions like get_job_details and get_recent_runs are scoped differently. A few pairs like search_project_objects and individual list functions could cause confusion, but descriptions generally clarify.

Naming Consistency4/5

Majority follow verb_noun pattern (e.g., create_dataset, delete_recipe). Some deviations exist (check_dataset_metrics instead of get_, batch_update_objects as a prefix), but overall consistency is high with no mixed conventions.

Tool Count3/5

43 tools is high, but the Dataiku platform is complex, covering datasets, recipes, scenarios, projects, and system resources. While some tools could be consolidated (e.g., multiple scenario getters), the count is borderline but reasonable for the domain.

Completeness4/5

Covers CRUD for main objects, plus build, run, test, validate, search, batch operations, and project-level exports. Missing delete_project and user management, but core workflows are well-supported with no dead ends.

Maintenance

ActivityInactive

ResponsivenessOutdated data

Resources

Related MCP Connectors

Artificial Wit AI
com.artificialwit
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
ERP Systems CRM Knowledge & Memory
2
https://api.artificialwit.com/mcp
LeadFoxConnect
io.github.LeadFox-Shay
Marketo MCP server for AI. 130 tools to operate Marketo from Claude, Cursor, or ChatGPT.
Marketing CRM
2
https://app.leadfoxconnect.com/mcp
mcp
dev.augments
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
Developer Tools Documentation Access
2127
https://mcp.augments.dev/mcp
BigQuery MCP by InsightfulPipeA
com.insightfulpipe
Hosted BigQuery MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Databases Data Platforms Cloud Platforms
41
https://bigquery.insightfulmcp.com/

Related MCP Servers

Salesforce MCP Server
Customer Data Platforms Databases
usama-dtc
A
license
A
quality
D
maintenance
An MCP server implementation that integrates Claude with Salesforce, enabling natural language interactions with Salesforce data and metadata.
Updated 2 years ago (2025-03-24 21:20 UTC)
8
59 npm
MIT
MCP-Server
File Systems Browser Automation Developer Tools
prajna-gajendra-acharya
A
license
Not graded
quality
D
maintenance
A production-ready MCP server with file management, HTTP requests, system info, and environment variable tools, plus a management UI and dual transport for Claude Desktop and Claude.ai.
Updated 7 months ago (2026-04-08 02:24 UTC)
512 npm
MIT
studiox-skills-mcpofficial
Developer Tools Documentation Access Knowledge & Memory
studioxdeveloper
A
license
Not graded
quality
D
maintenance
MCP server that provides access to over 100 development skills for frontend, backend, integration, design, devops, and process categories via Claude Code and other MCP clients.
Updated 10 months ago (2026-01-16 12:16 UTC)
MIT
OpenContext
Open Data Government Data Search
codeforanchorage
A
license
Not graded
quality
B
maintenance
An MCP server that connects to open data portals like CKAN and Socrata, enabling natural language querying of datasets via Claude.
Updated 17 hours ago (2026-11-12 18:06 UTC)
MIT

Dataiku DSS MCP Server

🚀 Quick Start

Prerequisites

Installation

Configuration

Claude Code Integration

📚 MCP Tool Catalog

Core Recipe Management Tools

Core Dataset Management Tools

Core Scenario Management Tools

🔧 Advanced Tools

Additional Dataset Tools

Additional Recipe Tools

Additional Scenario Tools

Advanced Tools

🔧 Usage Examples

Core Operations

Creating a Python Recipe

Building a Dataset

Getting Dataset Sample

Getting Scenario Logs

Exploring Project Structure

🏗️ Architecture

🔒 Security

📈 Monitoring

🤝 Contributing

Development Setup

📄 License

🔗 Links

📞 Support

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Salesforce MCP Server

MCP-Server

studiox-skills-mcpofficial

OpenContext