How to Use the data.world MCP in AutoGen

Q: How do AutoGen agents share data.world tool outputs?

When an agent calls getprojectdetails, the resulting JSON payload is published to the group chat. All other agents in the conversation can read this metadata and use it to form their arguments.

Q: Can an agent use this server to find datasets for another agent?

Yes. A search agent can call searchcatalog to locate relevant resources, then pass the dataset IDs to a query agent to fetch the details.

Q: Is my data.world account profile secure when using this MCP Server with AutoGen?

Yes. Access to your profile via getmyprofile is restricted to your local session. Vinkius uses token-level isolation to ensure your account permissions and activity logs are never leaked to external servers or shared with other workspaces.

Orchestrate AutoGen agents that debate project statuses and query data.world catalogs in real-time via MCP.

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 AutoGen

Create your Vinkius account to connect data.world to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Audits of data.world Projects

The `get_project_details` tool feeds real-time status updates, objective lists, and linked resource data directly into your AutoGen conversations over MCP. One agent can analyze project milestones while another cross-references them against active datasets. This debate ensures that your project tracking is accurate. The agents use the tool to resolve dependencies and flag missing resources before presenting a unified progress report to your team.

Validate Schemas via AutoGen MCP Server Tools

Your data engineer agent uses `get_dataset_details` to fetch field definitions and file listings, while your security agent checks the license terms. They debate whether a dataset is safe and structurally compatible for ingestion. If the license is restrictive or fields are missing, the security agent blocks the workflow. This consensus-driven approach prevents unsafe or broken datasets from entering your production pipelines.

Agent-Driven Collection Management

The `list_my_collections` tool allows your agents to review the collections you own or manage. Your coordination agent can assign specific collections to specialist agents based on the item counts and descriptions returned. By delegating collection analysis, your AutoGen team can parallel-process metadata reviews. The lead agent compiles the individual findings into a clean, structured summary of your catalog's health.

Setup guide

Set up data.world MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes data.world tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="data.world_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent data.world data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="data.world_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent data.world data")
    print(result.messages[-1].content)

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 AutoGen

When an agent calls `get_project_details`, the resulting JSON payload is published to the group chat. All other agents in the conversation can read this metadata and use it to form their arguments.

Yes, you register the tools with specific agents. For example, you can give `list_dataset_queries` only to your SQL analyst agent, while keeping your general conversational agents blind to the database schema.

Your credentials are encrypted and managed by Vinkius. The MCP tool adapter handles the handshake under the hood, so your AutoGen agents never see or expose your raw API tokens during their conversations.

Yes. A search agent can call `search_catalog` to locate relevant resources, then pass the dataset IDs to a query agent to fetch the details.

Yes. Access to your profile via `get_my_profile` is restricted to your local session. Vinkius uses token-level isolation to ensure your account permissions and activity logs are never leaked to external servers or shared with other workspaces.

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