If you're building AI agents that touch cross-border logistics, trade finance, or procurement workflows and need structured risk triage before human review, this is a trust-routing layer that takes evidence packs and returns auditable escalation decisions. It exposes three vertical workers over MCP: Middle Corridor deal risk gates for Kazakhstan routes, CIS secondary sanctions exposure checks, and agentic interaction trust scoring. Each worker validates evidence against schemas, flags gaps, and routes to allow, step up, escalate, or not-decision-ready outcomes without making factual determinations. Ships with HTTP API, A2A adapter, and Cloudflare Worker baselines, plus optional live retrieval against Watchman or OpenSanctions for sanctions screening. Good fit if you need reproducible geopolitical risk memos with source coverage audit trails baked in.
claude mcp add --transport stdio vassiliylakhonin-agenda-intelligence-md uvx agenda-intelligence-md