Gagelink MCP Server

by adeniyikayodee Your server? Claim it

local only

Gagelink runs on your own machine — the client starts it, so there is no endpoint to ping. 611 installs a week from pypi. Last commit 4 Sep 2026.

River level, streamflow, floods and basins from USGS, NOAA, Hub'Eau, UK Environment Agency, SWOT

Installs per day peak 597 · avg 174 · -46% w/w

a month agotoday

611

Installs / week

pypi · gagelink

Stars

0 open issues

4 Sep 2026

Last commit

0 releases in 90 days

MIT

License

Python

Nothing serious here today

Today is the operative word: we check Gagelink every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add gagelink -- uvx gagelink

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "gagelink": {
      "args": [
        "gagelink"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.gagelink]
command = "uvx"
args = ["gagelink"]

.cursor/mcp.json

{
  "mcpServers": {
    "gagelink": {
      "args": [
        "gagelink"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "gagelink": {
      "args": [
        "gagelink"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: GAGELINK_API_KEY (USGS Water Data API key, free from https://api.waterdata.usgs.gov/signup. Optional: without one the service allows 50 requests per hour rather than 1000.). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Gagelink

same job, measured the same way

USGS Water Monitoring

by olyport

Real-time water levels and flow rates from USGS stream gauges

3 tools answering

Floodwise

by qinisolabs

England flood-risk by postcode for AI agents — verified Environment Agency data, not guesses.

32 installs/wk local only

UK Environmental Intelligence MCP Server from MCPBundles

by mcpbundles

Access UK flood warnings, river levels, water quality, Met Office forecasts, and carbon data

answering

USGS Water Services MCP Server

by mansurjisan

USGS Water Services streamflow, flood stages, and peak events via waterservices.usgs.gov

70 installs/wk local only

Pondlog Usgs

by andrewschristison

USGS Water Services MCP server. Real-time streamflow, gage height, and site metadata from NWIS.

28 installs/wk local only

UK Waste Carrier Licence Monitor

by nero-engine

UK Environment Agency waste carrier licence records, with alerts on status and expiry.

answering

Ateam MCP

by ariekogan

Build, validate, and deploy multi-agent AI solutions from any AI environment.

444 installs/wk 59 tools answering

RiverWatch: USGS river levels & stream-flow gauges — per query

by a2awire

River levels & flood alerts: USGS gauges. $0.01/query. Register in-session — free testnet funds.

16 tools answering

Gagelink — questions

Answers built from our own checks of this server.

Why is there no uptime for Gagelink?

Gagelink runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package gagelink was installed 611 times last week.

How do I connect Gagelink?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls gagelink straight from pypi; nothing to host, nothing to sign up for.

How many people use Gagelink?

The pypi package gagelink was installed 611 times in the last week. Week over week that is -46%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Gagelink open source?

Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.