
Fluvigil MCP server
Which MCP servers are Fluvigil's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-26
- Registry namede.fluvigil/pegelverified in the MCP registry
The registry name sits under fluvigil.de. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-26
- Tools6
- Server calls itselffluvigil
- Server version1.2.0
- Protocol version2025-06-18
On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 179 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 2 of the 7 days it takes to judge reliability.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer577 ms
- Space in an agent's context≈ 1,315 tokensthe definitions of all its tools (6), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results6 of 6 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · watch river water levels on a live map
- not sure · get alerts when a gauge crosses a threshold
- not sure · query normalised flood data via API or MCP
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_stationsSearch stations in Germany and its neighbouring countries — river gauges, groundwater wells, reservoirs, coastal gauges — by name or water body, optionally filtered by region (a German federal state or a country code). latestValue is…
get_flood_situationCurrent flood situation: stations with an active LHP flood class (1 small … 4 very large), optionally per federal state. Every result names the data provider in sourceNotice (search and flood situation: sourceNotices, keyed by…
get_stationMaster data of one station: measurement type, current value with its unit, thresholds (MNW/MHW, alert marks, as stored valueCentimeters), flood class, coordinates. Every result names the data provider in sourceNotice (search and flood…
get_readingsTime series for a station (downsampled to ≤200 points; history depth on this tier: last 90 days, default last 7 days). type "level" (default) → level series as stored valueCentimeters: centimetres above gauge zero for most gauges, but an…
get_weatherDaily weather forecast at the station coordinate (DWD data via Bright Sky).
get_forecastNewest published water-level forecast for a station: the median of the state agency model run, future points within the horizon. Only gauges whose state publishes numeric forecasts have one, so an empty result is normal. Indicative, not…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"pegel": {
"type": "http",
"url": "https://fluvigil.de/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http fluvigil https://fluvigil.de/mcpclaude.ai, ChatGPT and other clients: add https://fluvigil.de/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.