How to Use the USGS Water Services MCP in Claude Code

Q: How do I execute a search for sites using USGS Water Services and Claude Code?

From your terminal, run the command calling getsites, specifying all necessary filters (e.g., bBox). The output is clean JSON that can be piped immediately into other shell scripts.

Q: What data types are available for batch processing with USGS Water Services and Claude Code?

You can process streamflow summaries using getdailyvalues, check historical groundwater levels via getgroundwaterlevels, or retrieve site metadata using getsites.

Q: Does the MCP Server support filtering by multiple criteria?

Yes. When calling getsites, you can combine filters like stateCd AND countyCd, ensuring your script only processes data from highly specific geographic areas.

Run water data pipelines from the terminal 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 USGS Water Services MCP to Claude Code

Create your Vinkius account to connect USGS Water Services 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 USGS Water Services with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate site discovery and filtering.

Use `get_sites` to programmatically discover USGS sites. You can pipe this output, filtered by stateCd or countyCd, into subsequent scripts for bulk processing. This is ideal for CI/CD jobs that need to validate infrastructure across multiple geographic areas before deployment.

Process historical data streams in batches.

Pipe the output of `get_daily_values` directly into a script. This tool pulls summarized daily metrics (mean, median, max, min) for specific time spans. You can feed this structured data to other command-line tools that require standardized CSV or JSON input.

Check groundwater levels in headless mode.

Run `get_groundwater_levels` from a cron job. This tool retrieves historical, manually-recorded groundwater measurements without needing any GUI. You just need to pass the required site identifiers. The script outputs clean data that can be immediately piped into logging or alerting systems.

Setup guide

Set up USGS Water Services 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 usgs-water-services-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest USGS Water Services transactions." It will automatically discover and invoke the available USGS Water Services tools.

Terminal

claude mcp add --transport http usgs-water-services-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 USGS Water Services 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": {
    "usgs-water-services-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 USGS Water Services. 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 USGS Water Services 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 USGS Water Services MCP in Claude Code

From your terminal, run the command calling `get_sites`, specifying all necessary filters (e.g., bBox). The output is clean JSON that can be piped immediately into other shell scripts.

You can process streamflow summaries using `get_daily_values`, check historical groundwater levels via `get_groundwater_levels`, or retrieve site metadata using `get_sites`.

Yes. You can automate checks for near real-time water data by running `get_instantaneous_values` in a loop, piping the results into an alerting system or log file.

You must specify whether you want daily, monthly, or annual statistics. Additionally, you need to provide approved data identifiers and date ranges for the tool to execute successfully.

Yes. When calling `get_sites`, you can combine filters like stateCd AND countyCd, ensuring your script only processes data from highly specific geographic areas.

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