data.world Connector for AI agents.
10 live capabilities
Find and manage enterprise data assets using natural language.
Waiting for input…
Why people use data.world
Data.world for Enterprise Data Governance
With this Connector, you can just ask your agent. It searches the catalog for you, pulls the relevant metadata, and summarizes the project status in seconds. You get the answers you need without the tab fatigue.
What Vinkius changes
You get a natural language interface for your entire data catalog.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Finding research data
A new analyst needs to find climate data.
- Real-world use case 02
Auditing project permissions
A data steward needs to audit permissions.
- Real-world use case 03
Checking project progress
A project lead wants to see progress.
Complete set · 10capabilities
The complete data.world capability set.
These are the exact actions your AI can choose when you ask it to work with data.world.
01—04
4 capabilities in this set.
Part of 10 available through data.world.
- 01 Capability
Get dataset details
Get field definitions, file listings, and license info for a specific dataset. This helps you understand the data structure before you start your analysis.
- 02 Capability
List recent activity
View a feed of updates, contributions, and new entries. It helps you stay current on what your team is doing.
- 03 Capability
List my collections
See all the collections you own or manage. This helps you keep track of your curated data groups.
- 04 Capability
List dataset queries
Pull all saved SQL or SPARQL queries for a dataset. It saves time by letting you reuse existing query logic.
05—07
3 capabilities in this set.
Part of 10 available through data.world.
- 05 Capability
List my datasets
See a list of all datasets you own on the platform. Use this to audit your personal data inventory.
- 06 Capability
Get my profile
Check your username and account permissions on the platform. Use this to verify your access levels quickly.
- 07 Capability
Get project details
See who is on a project and its current status. This gives you a quick overview of project health and members.
08—10
3 capabilities in this set.
Part of 10 available through data.world.
- 08 Capability
List project insights
Find the documented findings and visualizations in a project workspace. This helps you see what results have been achieved.
- 09 Capability
List my projects
Get a summary of all projects you own and your role in them. This is perfect for a quick portfolio overview.
- 10 Capability
Search catalog
Perform a full-text search for datasets and projects across the platform. Use this to find resources by title or tag.
Set up in minutes
One URL. Then ask data.world to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use data.world from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_tdQsdtjeyEJe7LirxBqlY8zM7HmSW2F7mw85gNx5/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it data.world, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable data.world for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_tdQsdtjeyEJe7LirxBqlY8zM7HmSW2F7mw85gNx5/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the data.world URL.
- Step 03
Save and start
Save the connection and enable data.world in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"dataworld": {
"url": "https://edge.vinkius.com/vk_preview_tdQsdtjeyEJe7LirxBqlY8zM7HmSW2F7mw85gNx5/mcp"
}
}
} - Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using data.world
Open Agent mode in chat and ask: "Using data.world, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"dataworld": {
"url": "https://edge.vinkius.com/vk_preview_tdQsdtjeyEJe7LirxBqlY8zM7HmSW2F7mw85gNx5/mcp"
}
}
} - Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using data.world
Ask Copilot: "Using data.world, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"dataworld": {
"url": "https://edge.vinkius.com/vk_preview_tdQsdtjeyEJe7LirxBqlY8zM7HmSW2F7mw85gNx5/mcp"
}
}
} - Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using data.world
Open Cascade and ask: "Using data.world, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"dataworld": {
"url": "https://edge.vinkius.com/vk_preview_tdQsdtjeyEJe7LirxBqlY8zM7HmSW2F7mw85gNx5/mcp"
}
}
} - Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using data.world
Ask Cline: "Using data.world, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add dataworld --transport http "https://edge.vinkius.com/vk_preview_tdQsdtjeyEJe7LirxBqlY8zM7HmSW2F7mw85gNx5/mcp" - Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using data.world
Ask Claude: "Using data.world, show me...". 10 tools are ready
Where the request belongs
Work data.world can move forward.
This is for data professionals who spend too much time asking 'where is this data?' or digging through metadata. It helps those who need to audit projects or find query definitions without manual searching.
Data Scientist
Uses the agent to find relevant datasets for research and quickly pull existing SQL queries to avoid rewriting code.
Data Steward
Monitors project statuses and audits data assets across the organization using chat commands.
Knowledge Manager
Explores organizational collections to plan data strategy and find published insights.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsAlation
Data catalog orchestration. search assets, audit metadata, and query data via AI.
Atlan
Search and discover data assets, business glossaries, classifications, policies, and personas directly via your AI agent.
Collibra
Enable your AI agent to manage data assets, domains, and communities via the Collibra Data Intelligence API.
Metabase (Business Intelligence & Analytics)
Manage your BI environment via Metabase. list dashboards, retrieve visual questions (cards), and search data entities.
Mode (Collaborative Data Platform)
Manage collaborative analytics via Mode. list data reports, explore organizational spaces, and audit data sources.
Starburst
Connect your AI to Starburst Enterprise. Query federated data lakes, manage access roles, and orchestrate complex data environments seamlessly.
Bring your own AI
Change the model, client or framework. Keep data.world connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about data.world.
The practical details behind the request, access and result.
How does the data.world MCP help my team find data?
It lets your AI agent search your entire enterprise catalog. You can ask questions about specific datasets or projects without leaving your chat interface.
Can I use this to manage my own projects?
Yes. You can use it to list your projects, check their status, and see which datasets are linked to them.
Does it work with SQL queries?
It lets your agent find and list saved SQL or SPARQL queries. This helps your team reuse existing logic instead of rewriting it from scratch.
How do I connect data.world to my AI agent?
You connect it through Vinkius. You'll just need your data.world API token from your user settings to get started.
Can I see insights from my datasets?
Yes. You can ask your agent to list the published insights and visualizations for any specific project or dataset.
How do I get a data.world API Token?
Log in to data.world, go to your user settings, and navigate to the Advanced > API Tokens section to generate a new token.
Can the agent run SQL queries?
This integration currently focuses on discovering assets and retrieving saved query definitions. Executing arbitrary SQL queries is managed via the data.world interface or specialized SDKs.
Does the integration support private datasets?
Yes, as long as the provided API Token has the necessary permissions, the agent can list and retrieve information for any dataset you have access to, including private ones.
One connection away
Give your agent a direct line to data.world.
Connect data.world once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available