Agent kit
Give agents a second opinion.
One MCP line sends a forecast panel to the same published Zeno model.
input
one question
many forecasts
zeno_check
MCP · HTTP · Python
output
forecast
range · warnings
{"mcpServers":{"zeno":{"url":"https://zenodivergent.dev/api/public/v1/mcp"}}}01 · inventory
Know what was measured.
Read served_as before acting. New domains are experimental, not magically validated.
Crypto price ranges
Zeno correction
+11.7%
Ensemble weather
Zeno correction
+5.6%
Deterministic weather
correction · no history
+6.2%
COVID-19 hospitalisations
correction · no history
+11.8%
Sea conditions
correction · no history
+3.2%
Prediction markets
reference kept
RSV
reference kept
FluSight
reference kept
ForecastBench
reference kept
Numinous AI forecasters
learn-only
02 · rules
Four things agents remember.
Especially the awkward one: ten agents on one underlying model are not ten independent opinions.
- 01
Many agents running on the same underlying model are not independent opinions. Never present agent count as a number of independent views.
- 02
Never quote experimental answers as evidence or proven results.
- 03
Never invent probabilities. If Zeno returns the reference, say so.
- 04
Never extrapolate a proven result from one source to another.
- 05
A forecast error never implies a profitable opposite trade. Say 'flag this signal for review', never 'trade against it'.
03 · endpoints
One model, several doors.
Public reads require no key. Team submissions remain authenticated.
/api/public/v1/checknone/api/public/v1/mcpnone/api/public/v1/schemanone/api/public/v1/release-manifestnone/api/public/v1/warnnone/api/public/arena/questionsnone/api/public/arena/forecastsClerk key (member rows) or Combiner key (f0); shared ZENO30_API_KEY is refused/api/public/v1/zeno30/combineCombiner key/api/public/v1/zeno30/identitynone