How to Use the Data.gov Catalog MCP in Claude

Q: Can Claude Desktop extract raw ingestion metadata from the Data.gov Catalog?

Yes. This MCP Server exposes getharvestrecordraw, which lets your agent fetch the unmodified source payload of any catalog entry. You get the exact metadata schema used during the original harvest process.

Q: How does the Data.gov Catalog MCP Server handle spatial filtering in Claude Desktop?

Your agent calls searchlocations to resolve place names to their official IDs. It then uses getlocationgeometry to retrieve GeoJSON boundaries, allowing Claude Desktop to filter dataset results by precise geographic regions.

Pull official U.S. government datasets directly into your Claude Desktop chat to build data models and verify public records.

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 Catalog MCP to Claude Desktop

Create your Vinkius account to connect Data.gov Catalog to Claude Desktop 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 Catalog with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Target datasets with spatial and keyword filters

`search_datasets` lets your agent pinpoint specific government files by filtering through thousands of active public records. You ask for climate data or census metrics, and your agent runs the query, filtering by location or publishing agency without you ever opening a browser. To refine these searches, `search_locations` and `get_keywords` feed autocomplete suggestions and exact taxonomy terms straight to your agent via this MCP Server. This prevents broken queries by ensuring your agent uses the exact naming conventions the federal catalog expects.

Inspect raw harvest metadata inside Claude Desktop

`get_harvest_record_transformed` pulls the normalized DCAT-US metadata payload directly into your local workspace. Your agent parses this structured data to map out pipeline schemas, verify data origins, and check update frequencies. When you need to troubleshoot ingestion errors or see the unaltered source, `get_harvest_record_raw` and `get_harvest_record` pull the exact upstream payloads. You get the raw truth of how the data entered the system, helping you debug parsing scripts in seconds.

Map geographic boundaries using location geometries

`get_location_geometry` extracts the precise GeoJSON boundary coordinates for any specific location identifier in the catalog. Your agent takes these coordinates and immediately prepares them for mapping tools, GIS software, or spatial analysis scripts. Instead of guessing regional coverages, `get_organizations` lists the publishing bodies so you can cross-reference which federal, state, or local agency owns the spatial data. This removes the manual hunting usually required when dealing with fragmented public sector geography.

Setup guide

Set up Data.gov Catalog MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

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.
3

Start a conversation

Open a new chat. The Data.gov Catalog MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Data.gov Catalog MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under datagov-catalog-mcp.

json

{
  "mcpServers": {
    "datagov-catalog-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Catalog 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 Catalog MCP in Claude Desktop

You type a natural language request for public data in your chat. Claude Desktop uses this MCP Server to run `search_datasets` behind the scenes, returning matched records, formats, and download links directly in your sidebar.

Yes. This MCP Server exposes `get_harvest_record_raw`, which lets your agent fetch the unmodified source payload of any catalog entry. You get the exact metadata schema used during the original harvest process.

Your agent calls `search_locations` to resolve place names to their official IDs. It then uses `get_location_geometry` to retrieve GeoJSON boundaries, allowing Claude Desktop to filter dataset results by precise geographic regions.

No. Vinkius manages the endpoint authentication, letting your agent query the entire public registry through a single secure token.

Every request runs through an ephemeral V8 sandbox that destroys itself immediately after execution. Your search parameters and retrieved metadata payloads are never cached, stored, or used for model training.

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