Data.gov Catalog MCP for AI. Query US Government Data with Precision.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Data.gov Catalog MCP connects your AI agent directly to the official US Government open data catalog. You can search thousands of datasets, track publishing organizations, and map precise geographic boundaries from agencies like NASA or NOAA using a single query.
This bypasses manual website browsing entirely.
What your AI can do
Get location geometry
Returns the precise GeoJSON boundary coordinates for a given location identifier.
Get harvest record raw
Retrieves the original, unmodified source data payload for inspection.
Get harvest record
Pulls metadata detailing how a specific dataset was originally added to the catalog.
Find specific public datasets by using keywords, organization names, and defined filters.
Get a complete list of all government agencies that publish data to the catalog.
Retrieve precise GeoJSON coordinates for any known location ID, allowing you to filter other datasets spatially.
View the original source data payload and the processed, structured version of a record.
Check which keywords are most common across the entire catalog and how many datasets use them.
Ask an AI about this
Waiting for input…
Data.gov Catalog: 8 Available Tools
These eight tools give you granular control over finding, inspecting, and mapping every piece of open data available in the US government catalog.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Data.gov Catalog on VinkiusGet Location Geometry
Returns the precise GeoJSON boundary coordinates for a given location identifier.
Get Harvest Record Raw
Retrieves the original, unmodified source data payload for inspection.
Get Harvest Record
Pulls metadata detailing how a specific dataset was originally added to the catalog.
Get Harvest Record Transformed
Gets a cleaned-up version of the record in a standardized format ready for use.
Get Keywords
Lists popular keywords and counts how many datasets reference each term across the...
Get Organizations
Provides a complete list of every publishing organization in the catalog.
Search Locations
Suggests location names and IDs that can be used to accurately narrow down a search area.
Search Datasets
Searches the entire government data catalog using specific keywords, filters, and...
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The Data.gov Catalog integration is available immediately — no restart needed.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Data.gov Catalog, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 8 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Getting data requires jumping through hoops.
Today, finding a specific dataset means opening the Data.gov portal, figuring out which agency has the right info, clicking through multiple filtering layers (like 'State' -> 'City' -> 'Water Quality'), and then downloading CSVs that may not even match what you needed.
With this MCP, the process stops being manual clicks. You just tell your agent exactly what you need—say, all datasets on water quality for a specific city—and it handles the complex chain of searches, filtering, and geometry retrieval automatically.
Get Location Geometry Data
Manually defining search areas is tedious. You'd have to find a location ID, then manually look up its boundary coordinates in a separate GIS tool, and finally paste those complex GeoJSON boundaries into your primary query.
Now, you just ask for the geometry using this MCP. It retrieves the precise coordinate set instantly, letting you immediately pass that structured data into other tools like `search_datasets` without leaving the chat.
What your AI can actually do with this
Need specific government data? This connection lets you talk to the Data.gov Catalog, giving your AI agent access to a massive repository of federal data. You don't have to navigate dozens of agency websites; you just ask for what you need—whether it’s a list of all publishing agencies or datasets related to climate modeling.
For example, if you are building a mapping tool, you can first find the precise geographic boundary for a city using its location ID. Then, you can use that geometry to filter down thousands of available records to only show data relevant to that area. You'll also get deep insight into how any dataset was created by inspecting both the original source files and the cleaned-up versions.
When you connect this MCP through Vinkius, your agent treats the entire government data ecosystem as one searchable pool. This means whether you need a simple keyword count or complex spatial filtering, it's all available right in your chat window.
019e3885-580b-73e1-9201-ff0571b05b26 
Here's how it actually works
The bottom line is that your agent handles the complex sequence of API calls needed to pull together multiple pieces of federal data into one readable answer.
Subscribe to this MCP on Vinkius and provide your API key or credentials.
Ask your AI client for a specific data task, like 'Find all water quality data near Miami.'
The agent calls the necessary functions (e.g., first locating the geometry, then searching datasets) and returns structured results directly to you.
Who is this actually for?
The data scientist who needs structured government inputs for a model, or the policy researcher tired of sifting through fragmented agency websites. This is built for people who need reliable, official source material and don't have time to manually browse multiple federal portals.
Needs structured geospatial boundaries or specific metadata payloads (like raw records) to train models without manual data cleaning.
Requires access to official agency lists and dataset counts to analyze federal policy gaps or identify key areas of government focus.
Integrates public data sources into a commercial application, needing structured formats like GeoJSON for mapping features.
What Changes When You Connect
Find relevant data without sifting through thousands of links. Use the search functionality to pull datasets based on keywords or specific organization filters.
Pinpoint exact areas using geometry. You can run a location ID through get_location_geometry and immediately use that boundary to filter your searches, making results hyper-local.
Understand data lineage. Don't just take the metadata; check the raw source payload or the transformed version of a record to verify data integrity.
Build knowledge maps quickly. Run get_organizations to get an exhaustive list of agencies, letting you target your research scope immediately.
Spot trends in government focus. Use get_keywords to see which topics are generating the most open data records right now.
See it in action
Mapping a specific environmental issue
A researcher needs all water quality reports for Chicago, Illinois. They first run search_locations to get the location ID, then use get_location_geometry with that ID. Finally, they pass the resulting GeoJSON boundary into search_datasets to filter only relevant datasets.
Auditing data source reliability
A developer needs to know if a dataset's metadata is complete. They find a promising record and use get_harvest_record_raw to check the original, unmodified payload before building their application logic.
Comparing federal focus areas
A policy analyst wants to know if climate change is more frequently discussed than economic development. They run get_keywords and then compare the resulting dataset counts for 'climate' versus 'economy'.
Listing all data providers
Someone building a directory of government open resources needs to know who publishes what. They simply call get_organizations to get an instant list of every contributing agency.
The honest tradeoffs
Searching by general topic only
Asking the agent, 'Tell me about data for water quality.' This yields too many results because it lacks geographic or source constraints.
Instead, first use search_locations to get a specific boundary ID. Then, combine that with get_location_geometry before running search_datasets. That locks the search down properly.
Assuming data structure is consistent
Building an app based on only the 'transformed' record without checking the original source, which might contain critical caveats.
Always check get_harvest_record_raw alongside get_harvest_record_transformed. The raw payload tells you what the data actually was.
Using a single keyword search
Simply searching for 'NASA' results in thousands of records, making it impossible to find the right dataset quickly.
First use get_keywords to narrow down related terms (e.g., finding both 'climate' and 'global'). Then, run a targeted search using those specific keywords with search_datasets.
When It Fits, When It Doesn't
Use this MCP if your task requires reliable, structured data originating from US government agencies—think mapping, policy analysis, or official record keeping. It's ideal when you need to go deep into metadata, like comparing the raw source payload against a cleaned-up version.
Don't use it if: 1) You are researching private company data; this is strictly federal information. 2) Your query is highly abstract and doesn't relate to geography or known agencies (e.g., 'What's the general vibe of US politics?'). In those cases, you need a different knowledge base that can interpret subjective text rather than structured records.
Questions you might have
How do I use get_location_geometry with search_datasets? +
You first run get_location_geometry using a location ID to pull the specific boundary coordinates. You then pass those exact boundaries into your query when calling search_datasets. This limits results perfectly.
What is the difference between get_harvest_record and get_harvest_record_raw? +
The raw record gives you the original, untouched source data payload. The standard harvest record provides metadata about how that dataset was initially ingested into the catalog.
Can I use get_keywords to find a specific type of dataset? +
No, get_keywords only tells you which topics are popular and how many datasets mention them. To actually find those datasets, you must run the results through search_datasets.
How do I list all available government agencies? +
Use get_organizations. It returns a complete list of every publishing organization that contributes data to the catalog. This is your starting point for scoping research.
When using search_datasets, what do I need regarding API keys or authentication? +
You must provide an API key if your proxy requires it. The process is simple: connect the MCP via Vinkius and supply your required credentials at the connection step. This ensures your agent can access the full US Government repository.
If I run get_location_geometry and receive an error, what does that usually mean? +
An error typically means the provided location ID is invalid or hasn't been fully indexed. Double-check the ID against the output of search_locations first. If the ID is correct, you might be hitting a temporary service limit.
What structure does get_harvest_record_transformed provide for my data? +
It returns a standardized DCAT-US payload structure. This transformed format makes it easy to parse common metadata fields like publication date and spatial bounding boxes, regardless of the original source schema.
How can I filter search_datasets using multiple criteria simultaneously? +
You combine filters directly in your query prompt. For instance, you can specify both a keyword AND an organization slug. The MCP handles prioritizing these combined parameters to narrow down results efficiently.
Can I search for datasets within a specific geographic area? +
Yes! Use search_locations to find a location ID, then get_location_geometry to get the GeoJSON. Finally, pass that to search_datasets with the spatial_geometry parameter.
How do I find datasets from a specific agency like NASA? +
Use the search_datasets tool and provide 'nasa' in the org_slug parameter. You can combine this with a search query q for more specific results.
What is the difference between raw and transformed harvest records? +
The get_harvest_record_raw tool returns the original metadata from the source agency, while get_harvest_record_transformed returns the data mapped to the standard DCAT-US schema used by Data.gov.
We've already built the connector for Data.gov Catalog. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 8 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.