Watershed MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Watershed MCP Serverwhich is cleaner, the Potomac or the Colorado River?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Watershed MCP Server
Live watershed data as MCP tools, built for owockibot.xyz bounty #477 ($10 USDC). Exposes river queries, USGS gauge readings, and EPA compliance rankings.
What it does
Five tools over the stdio MCP transport:
Tool | Source | Returns |
| USGS Water Services | Active stream gauges by river name (needs a 2-letter |
| USGS Water Services | Active gauges within a radius of a lat/lng (radius capped at ~35 mi by USGS bbox limits) |
| USGS NWIS live IV feed | Latest water-quality readings for a gauge as ecological-sensor readings conforming to the #450 JSON schema (draft 2020-12, |
| EPA ECHO CWA REST | Regional compliance aggregates: facilities, violations, inspections, penalties, plus a 0-100 compliance score and letter grade |
| EPA ECHO CWA REST | Rank multiple locations best-to-worst by compliance score |
All data sources are public and require no API keys. The vendored #450 schema lives in
schema/ecological-sensor-reading.schema.json
(original: xtratrezzy/ecological-sensor-schema,
submitted for bounty #450).
Related MCP server: mcp-usgs-water-data
Setup
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txtRun
Stdio (for Claude Desktop / MCP clients):
python -m watershed_mcp.serverClaude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"watershed": {
"command": "/path/to/repo/.venv/bin/python",
"args": ["-m", "watershed_mcp.server"],
"cwd": "/path/to/repo"
}
}
}Example session
> search_rivers("Colorado", state="co", limit=3)
{"count": 3, "sites": [{"site_no": "09163500", "station_name": "COLORADO RIVER NEAR COLORADO-UTAH STATE LINE", ...}]}
> get_gauge_readings("09163500")
{"site": {...}, "schema_ref": "https://github.com/xtratrezzy/ecological-sensor-schema/...",
"readings": [
{"schema_version": "1.0.0", "sensor_id": "USGS:09163500:00010", "sensor_type": "water_quality",
"parameter": "temperature", "value": 17.8, "unit": "celsius",
"timestamp": "2026-09-29T00:45:00.000-06:00",
"location": {"lat": 39.0, "lng": -109.05},
"source": "USGS NWIS Water Services via owockibot bounty #477 watershed MCP server",
"quality_flag": "raw", ...},
... ]}
> epa_compliance_ranking(38.9, -77.03, radius_miles=20)
{"facilities": 3342, "violations_last_4_quarters": 175, "compliance_score": 94.8, "grade": "A", ...}Tests
python tests/test_server.pyThe test harness spawns the server over real stdio MCP, runs initialize /
tools/list / tools/call against live USGS and EPA endpoints, and validates
every gauge reading against the vendored #450 schema with
jsonschema.Draft202012Validator.
Submission / deploy notes (for the claimer)
Create a public GitHub repo (e.g.
watershed-mcp), push this directory.Zip the repo (excluding
.venv/) and upload to Arweave (e.g. via ardrive orarweaveCLI) — the bounty asks for an Arweave-hosted build.Claim bounty #477 on owockibot.xyz with the GitHub repo URL + Arweave link in the submission. Note the proposer-priority window: only wallet
0xbc97e858bec05ba05be1e3bd63f65d3cbbecc4may claim until 2026-09-29T20:03:00Z; claims open to everyone after that.
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Real-time water levels and flow rates from USGS stream gauges
Query real-time and historical USGS water data from ~8,000 stream gages and groundwater wells.
River levels & flood alerts: USGS gauges. $0.01/query. Register in-session — free testnet funds.
Access UK flood warnings, river levels, water quality, Met Office forecasts, and carbon data
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceProvides access to real-time water data from the USGS Water Services API, allowing users to fetch instantaneous measurements like stream flow, gage height, temperature, and water quality parameters from thousands of monitoring stations across the US.3-
- AlicenseAqualityBmaintenanceEnables querying USGS water data including real-time and historical streamflow, gage height, and water temperature from USGS gauges across the United States.3MIT
- AlicenseNot gradedqualityBmaintenanceProvides real-time water temperature and tide predictions for any lake, river, ocean, bay, or beach using NOAA, USGS, and other sources.20 PyPIMIT
- AlicenseAqualityAmaintenanceProvides hydrology data (river levels, streamflow, flood forecasts, water quality) from USGS, NOAA, and SWOT, preserving units, datums, timezones, and data quality for AI agents.1381 PyPIMIT