How to Use the Data.gov Catalog MCP in Claude Code

Q: How can I use Claude Code to monitor the Data.gov Catalog for new datasets about a specific topic?

Write a simple shell script. Use claude to call the searchdatasets tool with your keywords and a date filter, then run it as a cron job. You can pipe the results to a notification service.

Q: Can I get a list of all keywords from the Data.gov Catalog using Claude Code in my terminal?

Yes. Just run the command to invoke the getkeywords tool. It will print a JSON object with the keywords and their usage counts directly to standard output.

Q: Is it possible to find a specific county's GeoJSON boundary from the Data.gov Catalog with Claude Code?

It is. Use the searchlocations tool to find the location ID for the county. Then, feed that ID to the getlocationgeometry tool to get the GeoJSON data, which you can save to a file or pipe elsewhere.

Pipe the entire US open data catalog into your shell scripts and CI/CD pipelines with Claude Code.

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 Code

Create your Vinkius account to connect Data.gov Catalog to Claude Code 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Data.gov in Your Terminal

The `search_datasets` tool lets you query the Data.gov catalog from your command line. You can pipe the JSON output directly to tools like `jq` for filtering or other scripts for processing. This makes automation simple. Set up a cron job that runs a `search_datasets` query every night to find new entries related to your work. No manual website checking needed.

Scriptable Org and Keyword Lists

The `get_organizations` tool dumps a clean list of all publishing agencies. It's perfect for building scripts that iterate through every data source. You can combine tools in one-liners. For instance, use `get_organizations` to find an agency's name, then pipe that into a `search_datasets` command to see everything they've published. It's all designed for the command line.

A Headless Data.gov MCP Server

This MCP server is built for headless operation. Use `get_harvest_record` to check the source of a dataset as part of a data validation pipeline in a GitHub Action. Every tool returns structured data, so you're not screen-scraping or parsing messy HTML. Whether you're using `get_keywords` or `get_location_geometry`, the output is predictable JSON, ready for your next command.

Setup guide

Set up Data.gov Catalog MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see datagov-catalog-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Data.gov Catalog transactions." It will automatically discover and invoke the available Data.gov Catalog tools.

Terminal

claude mcp add --transport http datagov-catalog-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Data.gov Catalog MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "datagov-catalog-mcp": {
      "type": "url",
      "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 Code

Write a simple shell script. Use `claude` to call the `search_datasets` tool with your keywords and a date filter, then run it as a cron job. You can pipe the results to a notification service.

Yes. Just run the command to invoke the `get_keywords` tool. It will print a JSON object with the keywords and their usage counts directly to standard output.

It is. Use the `search_locations` tool to find the location ID for the county. Then, feed that ID to the `get_location_geometry` tool to get the GeoJSON data, which you can save to a file or pipe elsewhere.

The MCP server handles authentication, rate limiting, and provides a consistent interface across all tools. You connect once with `claude mcp add` and you're done. You don't have to manage API keys or endpoints for every script you write.

Even though the server handles public data like dataset metadata, your connection is still protected. Vinkius isolates each request in a zero-trust, ephemeral sandbox. Authentication is managed via a single Vinkius token, so your local credentials are never transmitted.

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