# Data.gov MCP for AI Agents MCP

> Data.gov connects your AI client directly to over 300,000 open datasets from US federal agencies. You can search by topic, find specific organizations like NASA or USDA, and pull detailed metadata on everything from climate models to student performance data. It's the single source for public records research.

## Overview
- **Category:** knowledge-management
- **Price:** Free
- **Tags:** open-data, federal-datasets, public-records, data-catalog, research-data

## Description

Need to dig into government data? This MCP lets your AI agent converse with the entire Data.gov catalog. You don’t need to mess with API keys or write complex queries just to get started. Instead, you talk naturally about what you're looking for—say, 'Give me all datasets on water quality in Florida.' The system handles the search across hundreds of agencies and topics.

It provides structure by allowing you to explore data groups like 'Health' or 'Finance,' or drill down into specific agencies like the Census Bureau. If your research requires understanding what kind of files are available, it shows formats ranging from JSON to CSV. Connecting this through Vinkius gives your AI client access to all these resources in one place, letting you spend time analyzing data instead of building connections.

## Tools

### get_dataset
Retrieves full metadata for a specific dataset ID or name, including licenses and download options.

### get_group
Gets details about broad topic groups like 'climate' or 'health', listing associated datasets.

### get_organization
Provides information on a specific federal agency, including its contact info and published data sets.

### get_organization_datasets
Lists all available datasets published by one particular organization you specify.

### get_status
Checks the overall API status of Data.gov, providing total counts for groups, organizations, and tags.

### get_tag
Returns details about a specific tag (like 'public-safety'), along with how many datasets use it.

### get_tag_datasets
Retrieves all dataset titles and download links associated with a given descriptive tag.

### get_group_datasets
Lists all datasets that fall under a specific topic group, such as 'education'.

### list_groups
Returns a list of every major topic group available on the site (e.g., finance, climate).

### list_organizations
Lists all federal agencies that have contributed data to Data.gov.

### list_resource_formats
Displays a list of all possible file formats (JSON, CSV, etc.) available for download.

### list_tags
Shows every active tag used across the catalog and how many datasets are associated with it.

### search_datasets
Performs a comprehensive search using free text, filtering by organization or group to find specific public records.

## Prompt Examples

**Prompt:** 
```
Search for climate change data from NOAA.
```

**Response:** 
```
**Climate Data Report: US Federal Sources**

*   **NOAA Climate Data:** Comprehensive temperature and sea level readings. (Format: JSON, Updated: 2024-05-15)
*   **EPA Greenhouse Gas Emissions:** Yearly emissions by state. (Format: CSV, Updated: 2023-01-01)

You can download both datasets directly via the provided links for immediate analysis.
```

**Prompt:** 
```
What education records are available?
```

**Response:** 
```
**📚 Education Datasets Found:**

The following data sets cover student performance and spending:

| Dataset Name | Organization | Key Topics | Format | 
| :--- | :--- | :--- | :--- |
| NAEP Assessment Data | Dept. of Ed. | Student Grades, Spending | CSV | 
| College Scorecard | Dept. of Ed. | Enrollment, Cost | JSON | 

Start by reviewing the full metadata for any title above.
```

**Prompt:** 
```
Show me all datasets related to water quality in Florida.
```

**Response:** 
```
**💧 Water Quality Datasets (Florida Focus):**

We found 8 relevant records from various sources:

*   **State Pollutant Levels:** EPA, measuring pH and turbidity. (Latest: 2024-06)
*   **River Basin Flow Rates:** USGS, tracking flow volume. (Format: XML)

Please specify if you need data for a certain year to narrow down the search.
```

## Capabilities

### Search for datasets across multiple topics
Find specific public datasets by searching keywords and filtering results by organization or tags.

### Identify relevant government organizations
List federal agencies, like the EPA or NOAA, to see what kind of data they publish.

### Browse datasets by general topic area
Explore pre-grouped topics such as agriculture, climate, or public safety to narrow your focus quickly.

### Get detailed information on a dataset
Retrieve the full metadata, license details, and resource download links for any specific data set ID.

### Check available data formats
List all possible file types (CSV, JSON, XML) so you know what format your final dataset will be in.

## Use Cases

### Correlating climate trends with agricultural yields
A researcher needs to compare NOAA's historical temperature data with USDA crop reports. They ask their agent to search for both datasets, using `search_datasets` and then getting the details via `get_dataset` for reliable download links.

### Verifying a news report on public safety statistics
A journalist needs hard data. They ask their agent to look up all available datasets tagged 'public-safety' using `get_tag_datasets`, then use `get_organization` to see which federal agency published the most recent information.

### Building a dashboard on educational spending
A developer needs structured data for a new app. They ask their agent to list all groups, find 'education', then use `get_group_datasets` to pull titles and download links from relevant departments.

### Mapping US environmental policy changes
A student needs to understand the scope of federal resources. They ask their agent to list all available resource formats using `list_resource_formats`, then use `search_datasets` filtered by 'EPA' and 'water quality'.

## Benefits

- Search over 300,000 records instantly: Use `search_datasets` to find precise data sets across agriculture, health, or climate without knowing the exact dataset ID.
- Understand where the data comes from: You can list all organizations using `list_organizations`, letting you trace a topic back to its original federal source (e.g., NASA).
- Explore by theme, not just keywords: Use `get_group_datasets` or `list_groups` to browse entire domains like 'Education' and see related data sets.
- Know the file format upfront: Before running a query, use `list_resource_formats` to confirm if your data is available as clean JSON or CSV for immediate use in code.
- Get complete context on any dataset: Running `get_dataset` gives you all the metadata—the license, the date it was last updated, and what fields are included.

## How It Works

The bottom line is you get conversational access to massive, complex public data without writing a single API call.

1. Subscribe to this MCP on Vinkius and connect it to your AI client. No API key is needed because all the data is public domain.
2. Ask your agent a question like, 'Show me all datasets related to education spending.'
3. The agent executes the necessary search across the catalog and returns structured results with titles, sources, and download options.

## Frequently Asked Questions

**Do I need an API key?**
No! Data.gov data is public domain and freely accessible. No authentication required.

**How many datasets are available?**
Data.gov catalogs 300,000+ datasets from over 200 federal agencies including NASA, USDA, EPA, NOAA, Department of Education, Census Bureau and many more.

**What organizations publish data?**
Over 200 federal agencies including NASA, USDA, EPA, NOAA, Department of Education, Census Bureau, Department of Transportation, FBI, CDC, FDA and many more.

**What formats are available?**
Common formats: CSV, JSON, XML, Shapefile, GeoJSON, PDF, HTML, RDF, KML, ZIP. Use list_resource_formats to see all available formats.