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.

data.world MCP Server for CrewAI 10 tools — connect in under 2 minutes

Name: data.world
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 10 Tools Framework

Connect your CrewAI agents to data.world through the Vinkius — pass the Edge URL in the `mcps` parameter and every data.world tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from crewai import Agent, Task, Crew

agent = Agent(
    role="data.world Specialist",
    goal="Help users interact with data.world effectively",
    backstory=(
        "You are an expert at leveraging data.world tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token — get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in data.world "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 10 available tools "
        "and what they can do."
    ),
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About data.world MCP Server

Integrate data.world, the enterprise data catalog and collaborative data platform, directly into your AI workflow. Discover datasets, monitor data projects, and explore saved queries and insights using natural language.

When paired with CrewAI, data.world becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call data.world tools autonomously — one agent queries data, another analyzes results, a third compiles reports — all orchestrated through the Vinkius with zero configuration overhead.

What you can do

Data Discovery — Search the entire data.world catalog for relevant datasets and projects.
Asset Management — List and retrieve detailed information for datasets and projects you own or manage.
Collection Oversight — Explore curated collections of data assets within your organization.
Query & Insight Access — List saved SQL/SPARQL queries and published insights for your data projects.

The data.world MCP Server exposes 10 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect data.world to CrewAI via MCP

Follow these steps to integrate the data.world MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py — CrewAI auto-discovers 10 tools from data.world

Why Use CrewAI with the data.world MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with data.world through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles — one agent researches, another analyzes, a third generates reports — each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass the Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

data.world + CrewAI Use Cases

Practical scenarios where CrewAI combined with the data.world MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries data.world for raw data, then a second analyst agent cross-references findings and flags anomalies — all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries data.world, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain data.world tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries data.world against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

data.world MCP Tools for CrewAI (10)

These 10 tools become available when you connect data.world to CrewAI via MCP:

get_dataset_details

Includes field definitions, file listings, tags, and license information. Get detailed information for a specific dataset

get_my_profile

world. Returns profile attributes including username, display name, and account-level permissions. Retrieve metadata for the current authenticated user

get_project_details

Resolves project members, associated objective, and the current status of linked resources. Get detailed information for a specific project

list_dataset_queries

Returns a list of saved query definitions, including their language (SQL/SPARQL) and creator metadata. List all saved SQL or SPARQL queries for a dataset

list_my_collections

Returns collection identifiers, descriptions, and item counts. List all collections you own or manage

list_my_datasets

world catalog for datasets owned by the authenticated user. Returns a list of dataset metadata including title, visibility (public/private), and timestamp of last modification. List all datasets you own on data.world

list_my_projects

Returns project summaries including role (owner/contributor), creation date, and linked datasets. List all projects you own on data.world

list_project_insights

Insights represent documented findings and data visualizations attached to the project workspace. List all insights published within a project

list_recent_activity

Returns a stream of activity logs including dataset updates, project contributions, and new collection entries. List recent activities in your data.world account

search_catalog

world index. Supports full-text search across titles, descriptions, and tags. Returns a ranked list of matching resources. Search for datasets and projects across data.world

Example Prompts for data.world in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with data.world immediately.

"Search for datasets related to 'Global Climate Change'."

"List all SQL queries saved in my project 'Sales Analysis 2024'."

"Show me the insights published in dataset 'Retail Trends'."

Troubleshooting data.world MCP Server with CrewAI

Common issues when connecting data.world to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts — check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

The Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

data.world + CrewAI FAQ

Common questions about integrating data.world MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily — when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.