How to Use the data.world MCP in Mastra AI

Q: Can Mastra AI build a workflow that finds new data.world datasets and analyzes them?

Absolutely. You can chain tools together. Use searchcatalog to find datasets, then pass the results to getdatasetdetails to inspect their schema and files within the same Mastra AI workflow.

Q: Can I require human approval for certain data.world actions in Mastra AI?

Yes. Mastra AI supports requireToolApproval. You can configure your agent to pause and wait for a human to confirm before it executes a sensitive operation on data.world, like modifying a project.

Q: What does it mean to list tools from this MCP Server?

When you call mcpClient.listTools(), you're getting a list of all available data.world operations. You can then provide all or just a subset of these to your agent, limiting its capabilities to only what's needed for its task.

Build resilient data.world workflows with Mastra AI. Automate dataset management with branching logic and automatic retries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect data.world MCP to Mastra AI

Create your Vinkius account to connect data.world to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup data.world with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Data Discovery Workflows

Create agents that systematically explore your data.world assets. A Mastra AI workflow can `search_catalog` for new datasets, then use `get_dataset_details` to check if they meet specific criteria, like having a 'public' license. Build conditional logic around the results. For example, if a dataset has the right tags, your agent can automatically add it to a project. Mastra's engine handles the multi-step process, retrying if an API call fails.

A Resilient data.world MCP Server

This isn't just about calling an API; it's about building reliable automation. This MCP Server gives your Mastra AI agent the tools to interact with data.world, from listing collections with `list_my_collections` to checking `list_recent_activity`. Mastra's workflow engine wraps these tool calls with features like exponential backoff. If a call to `get_my_profile` fails, it retries automatically. You define the high-level logic, and Mastra handles the execution details.

Monitor and Manage Projects

Set up an autonomous agent to watch over your data.world projects. It can periodically run `list_my_projects` and then `get_project_details` for each one to check its status and member list. If a project's status changes, your workflow can trigger other actions, like sending a notification or running a new query with `list_dataset_queries`. Mastra's resilience means your monitoring won't stop because of a temporary network issue.

Setup guide

Set up data.world MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All data.world tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "dataworld-mcp-client",
  servers: {
    "dataworld-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "data.world Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to data.world tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent data.world transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by data.world. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect data.world now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about data.world MCP in Mastra AI

Absolutely. You can chain tools together. Use `search_catalog` to find datasets, then pass the results to `get_dataset_details` to inspect their schema and files within the same Mastra AI workflow.

Mastra has built-in resilience. If a tool call fails, it can automatically retry with exponential backoff. You can define complex error handling, like trying an alternative action or sending an alert if a data.world operation fails repeatedly.

Yes. Mastra AI supports `requireToolApproval`. You can configure your agent to pause and wait for a human to confirm before it executes a sensitive operation on data.world, like modifying a project.

When you call `mcpClient.listTools()`, you're getting a list of all available data.world operations. You can then provide all or just a subset of these to your agent, limiting its capabilities to only what's needed for its task.

Your connection is secured through Vinkius. The server only accesses data.world metadata like dataset details and project summaries. Mastra AI interacts with the Vinkius endpoint, so your core data.world credentials aren't part of your agent's code.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript