# data.world MCP for AI Agents AI Agent Connect

> data.world connects your AI agent to an enterprise data catalog. It lets your agent find datasets, check project statuses, and pull saved queries using natural language. Use it to navigate complex data environments without manual searching.

## Overview
- **Category:** knowledge-management
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_tdQsdtjeyEJe7LirxBqlY8zM7HmSW2F7mw85gNx5/ai-agent-connect
- **Tags:** data-catalog, metadata-management, data-governance, collaborative-data, data-discovery, sql-queries

## Description

This Connector lets you treat your enterprise data catalog like a searchable knowledge base. Instead of clicking through endless folders or hunting for the right owner, you can just ask your agent where specific datasets live or what's in a certain project. It connects your agent to the full data.world API, making it possible to pull dataset definitions, find saved SQL queries, and keep tabs on project progress. You'll find that it moves the heavy lifting of data discovery out of the browser and into your chat window. It's part of the Vinkius catalog, which makes it easy to plug into your existing workflow without a lot of setup. You get a clear view of your own assets, your organization's curated collections, and the actual insights your team has already published.

## Tools

### 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.

### list_recent_activity
View a feed of updates, contributions, and new entries. It helps you stay current on what your team is doing.

### list_my_collections
See all the collections you own or manage. This helps you keep track of your curated data groups.

### list_dataset_queries
Pull all saved SQL or SPARQL queries for a dataset. It saves time by letting you reuse existing query logic.

### list_my_datasets
See a list of all datasets you own on the platform. Use this to audit your personal data inventory.

### get_my_profile
Check your username and account permissions on the platform. Use this to verify your access levels quickly.

### get_project_details
See who is on a project and its current status. This gives you a quick overview of project health and members.

### list_project_insights
Find the documented findings and visualizations in a project workspace. This helps you see what results have been achieved.

### list_my_projects
Get a summary of all projects you own and your role in them. This is perfect for a quick portfolio overview.

### search_catalog
Perform a full-text search for datasets and projects across the platform. Use this to find resources by title or tag.

## Prompt Examples

**Prompt:** 
```
Search for datasets related to 'Global Climate Change'.
```

**Response:** 
```
I've found several datasets related to 'Global Climate Change', including:

* **NASA GISS Surface Temperature**
* **UN Statistics on Emissions**

Would you like to see the field definitions or license info for any of these?
```

**Prompt:** 
```
List all SQL queries saved in my project 'Sales Analysis 2024'.
```

**Response:** 
```
Project **Sales Analysis 2024** has 3 saved SQL queries:

| Query Name | Language | Creator |
| :--- | :--- | :--- |
| Monthly Revenue Recap | SQL | DataTeam_Alpha |
| Top Performing Regions | SQL | DataTeam_Alpha |
| Churn Rate Analysis | SQL | DataTeam_Alpha |

Should I retrieve the full definition for any of them?
```

**Prompt:** 
```
Show me the insights published in dataset 'Retail Trends'.
```

**Response:** 
```
I've found 2 insights for **Retail Trends**:

* **Q1 Growth Patterns**
* **Customer Demographics Shift**

Both were published by **DataTeam_Alpha**. Would you like to see the full content of these insights?
```

## Capabilities

### Search the entire catalog
Find datasets and projects across the platform using full-text search.

### Get dataset field details
Pull definitions, tags, and license info for specific data assets.

### List owner-specific projects
See all projects you own along with their current status and members.

### Find saved SQL queries
Retrieve saved SQL or SPARQL query definitions for any dataset.

### Browse organizational collections
Explore curated groups of data assets within your company.

## Use Cases

### Finding research data
A new analyst needs to find climate data. They ask the agent to search_catalog for 'Global Warming' and then get_dataset_details to see the field names.

### Auditing project permissions
A data steward needs to audit permissions. They use get_my_profile to check their own access and list_my_projects to see what they manage.

### Checking project progress
A project lead wants to see progress. They use get_project_details to see who's working on a specific task and list_project_insights to see the results.

### Reusing SQL logic
A researcher needs a starting point for a new report. They use list_dataset_queries to see what SQL has already been written for a specific dataset.

## Benefits

- Stop hunting for files by using search_catalog to find datasets across the entire platform instantly.
- Keep projects on track by checking current statuses and member roles with get_project_details.
- Share knowledge faster by pulling saved SQL or SPARQL definitions using list_dataset_queries.
- Maintain better oversight of your work by viewing your own assets with list_my_datasets.
- Stay updated on team progress by pulling a live feed of changes using list_recent_activity.
- Quickly understand data structures by pulling field definitions with get_dataset_details.

## How It Works

The bottom line is you get a natural language interface for your entire data catalog.

1. Connect the data.world MCP to your AI client via Vinkius.
2. Provide your data.world API Token from your user settings.
3. Ask your agent to find datasets, check project status, or list saved queries.

## Frequently Asked Questions

**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.