An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Datagov Catalog to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Pull official US government datasets directly into your AI agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 8 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 8 available through Data.gov.

  1. 01

    Get harvest record transformed

    This capability pulls the transformed DCAT-US payload for a specific harvest record. Use it to get structured metadata ready for analysis.

  2. 02

    Get organizations

    This capability retrieves the full list of organizations that publish data. It helps your agent identify specific agencies to query.

  3. 03

    Search locations

    This capability provides autocomplete for location names. It is the first step when you want to perform spatial filtering.

  4. 04

    Get harvest record

    This capability fetches metadata regarding how a dataset was ingested into the catalog. Use it to check the ingestion history of a record.

Capability set02 / 02

05-08

4 capabilities in this set.

Part of 8 available through Data.gov.

  1. 05

    Get harvest record raw

    This capability retrieves the original, unmodified source payload for a harvest record. It is useful for deep technical inspections.

  2. 06

    Get keywords

    This capability lists commonly used keywords and their associated dataset counts. Use it to identify trending topics in the catalog.

  3. 07

    Get location geometry

    This capability fetches the GeoJSON boundary for a specific location ID. It allows your agent to define exact geographic search areas.

  4. 08

    Search datasets

    This capability searches the entire catalog using keywords, agency filters, and sorting options. It is the primary way to find data.

Real work

What teams actually run

01

Automated Data Gathering

An agent can be tasked to find all NASA datasets regarding ocean temperatures and prepare them for a report.

02

Geospatial Research

You can use the agent to find datasets that fall within a specific city's GeoJSON boundary.

03

Metadata Auditing

A developer can use the agent to inspect the raw harvest records of a dataset to ensure data integrity.

04

Trend Identification

A researcher can ask the agent to find the most common keywords to see which topics are currently being prioritized by agencies.

Automate a task

Put Data.gov to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Data.gov works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Data.gov to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1019ms average. Fast in production.

Data.gov is checked daily against the live service.

Daily averagePeak 1302ms
Oct 3Today
Fastest day
779ms
Slowest day
1302ms
14-day trend
Improving-14%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 8 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Data.gov, so you can see the experience inside your AI.

It does not authenticate your account with Data.gov. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Data.gov Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_f564VZunubaqnMfft1dIIxySnAafP9NKhpaI9WS5/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Data.gov capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "datagov-catalog-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_f564VZunubaqnMfft1dIIxySnAafP9NKhpaI9WS5/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Data.gov in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Data.gov owners hand off.

This MCP is built for professionals who need to pull official government data into their local development or research environments.

  • 01

    Data Scientists

    They use the agent to find and pull relevant datasets for modeling without manual web searching.

  • 02

    Researchers

    They rely on the agent to grab official metadata and harvest records for academic studies.

  • 03

    Developers

    They use the agent to fetch structured GeoJSON and DCAT-US metadata for application integration.

FAQ

Questions Data.gov owners ask.

  • 01

    Do I need an API key to use this MCP?

    You can use the 'PUBLIC' setting to access the catalog. If your specific proxy requires a key, you can enter it during setup.

  • 02

    Which AI clients can I use with this?

    This MCP works with any compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 03

    Can I search for data by specific location?

    Yes. You can use the search_locations capability to find a location ID and then use get_location_geometry to get the GeoJSON boundary for spatial filtering.

  • 04

    What kind of data formats can my agent receive?

    Your agent can receive structured GeoJSON for spatial data and DCAT-US payloads for metadata.

  • 05

    Is this a directory of links?

    No. Vinkius hosts the MCP so it is a functional capability that your agent can actually execute to perform searches and data retrieval.

  • 06

    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.

  • 07

    How do I find datasets from a specific agency like NASA?

    Use the search_datasets capability and provide 'nasa' in the org_slug parameter. You can combine this with a search query q for more specific results.

  • 08

    What is the difference between raw and transformed harvest records?

    The get_harvest_record_raw capability 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.

Explore

More in Data Analytics

Suggestions

Connect Data.gov to Claude, Cursor, ChatGPT & more