How to Use the Data.gov MCP in CrewAI

Q: How can a CrewAI team collaborate to find and summarize new health data from Data.gov?

Assign a Researcher agent to call searchdatasets with query: "health" and sort: "metadatamodified desc". It passes the results to an Analyst agent, which then uses getdataset to fetch details and generate a summary.

Q: Can my agents find out what data formats are available before trying to download anything?

Absolutely. Have one of your agents run the listresourceformats tool. This will give it a complete list of all file types (like CSV, XML, JSON) available across the Data.gov catalog.

Q: How would a CrewAI team discover popular topics on Data.gov?

A "Discovery" agent could use listtags to get a list of all tags and their usage counts. It could then use gettagdatasets on the most frequent tags to explore what's currently trending. This MCP Server makes that data available.

Build autonomous research teams with CrewAI that dig through Data.gov, find insights, and act on them without you. This MCP server is their direct line to the data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Data.gov MCP to CrewAI

Create your Vinkius account to connect Data.gov to CrewAI 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.gov with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy a Research & Analysis Crew

Assign roles to your CrewAI agents. A "Researcher" agent can use `search_datasets` and `list_tags` to find relevant datasets on a topic like "climate change". It passes the most promising dataset IDs to the next agent. An "Analyst" agent then takes over. It uses `get_dataset` to pull the full details, including resource URLs and metadata. The whole process is powered by this single MCP, letting your agents focus on their tasks.

Build a Proactive Monitoring Team

Create a crew to watch for specific events. An "Observer" agent could run `get_organization_datasets` on a schedule for an agency like the FDA. Its only job is to detect changes. If the Observer finds a new dataset, it triggers a "Notifier" agent. This second agent's job is to use `get_dataset` to get the specifics and then send a formatted alert. An MCP makes this kind of inter-agent tool use possible.

Your Data.gov CrewAI Team

You can create highly specialized crews. Imagine a "Compliance" agent that uses `get_dataset` to check the `license` field of datasets found by another agent, ensuring they are cleared for use. This MCP server exposes all the tools your agents need to work together. One agent can `list_groups` to find topics, another can `get_group_datasets` to list data, and a third can `get_organization` to verify the source. CrewAI connects them into a single, autonomous workflow.

Setup guide

Set up Data.gov MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Data.gov tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Data.gov Analyst",
    goal="Access and analyze Data.gov data via MCP.",
    backstory="Expert analyst with direct Data.gov access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Data.gov transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

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

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Data.gov Analyst",
        goal="Access and analyze Data.gov data via MCP.",
        backstory="Expert analyst with direct Data.gov access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Data.gov transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

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

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.gov. 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.gov 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.gov MCP in CrewAI

Assign a Researcher agent to call `search_datasets` with `query: "health"` and `sort: "metadata_modified desc"`. It passes the results to an Analyst agent, which then uses `get_dataset` to fetch details and generate a summary.

Absolutely. Have one of your agents run the `list_resource_formats` tool. This will give it a complete list of all file types (like CSV, XML, JSON) available across the Data.gov catalog.

Yes. You can dedicate an agent to a single source. Just have it use `get_organization_datasets` with the specific organization's name or ID. It will only get back datasets published by that single entity.

A "Discovery" agent could use `list_tags` to get a list of all tags and their usage counts. It could then use `get_tag_datasets` on the most frequent tags to explore what's currently trending. This MCP Server makes that data available.

The server is designed to interact only with public, open-source data from the Data.gov catalog; this includes things like dataset metadata and agency names. Vinkius runs each MCP server in an ephemeral, zero-trust sandbox. For CrewAI, your agent's connection is stateless and secured via your private endpoint token.

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