Russia–NATO risk ladder

Connect it to your AI

Claude Code

claude mcp add --transport http risk-ladder https://mcp.russianato.site/mcp

Claude, ChatGPT, Cursor and other apps

Add it as a custom connector with this URL (Streamable HTTP):

https://mcp.russianato.site/mcp

Cursor, VS Code and other apps (mcp.json)

{
  "mcpServers": {
    "risk-ladder": {
      "url": "https://mcp.russianato.site/mcp"
    }
  }
}

Tools it offers

8 tools, as the server itself reported during our check on Oct 31, 2026.

• get_overviewStart here. Annual risk for the five escalation levels today, a year ago and in one year (optimistic / baseline / pessimistic), plus average intelligence tone per country. Every number carries its provenance (published /
• get_risk_ladderAnnual risk of each level on a date between one year ago and one year ahead of the data date. Past dates use the published forecast archive; future dates use the scenario model and also return cumulative risk from the da
• get_forecast_historyPublished Metaculus probabilities by 2035 for an attack on European NATO or a seizure of Baltic territory, with the annual conversion for each observation.
• get_intelligence_assessmentsPublic assessments by intelligence services and governments of 12 countries, newest first, with hand-coded tone from -2 to +2 for a military attack and for hybrid attacks, averages by country, check dates and links.
• get_sourcesThe 51 sources with what each says, how it is used, countries, check date and link. Filter by type (intel, research, method, forecast), country or text.
• get_other_forecastsPrediction markets and other numeric forecasts with a different event or horizon (Manifold, Polymarket, Metaculus, Good Judgment Open, Atlantic Council), with check dates and corrections.
• get_changelogSignificant changes to data, model and site, and the corrections history (what was wrong, what changed, who reported it).
• get_methodologyLevel definitions, formulas, current assumptions with check dates, the verbal probability scale and what the model deliberately does not do.

Questions