verdict-from-chain
Parse a raw RSK chain output into a typed Verdict struct — the driveshaft between RSK engine (Excrete) and Guardian navigator (Absorb). Takes drug name, event name, and the chain_output JSON object from pv-signal-to-action or vehicle-full-cascade. Returns a typed Verdict with signal_strength, causality, regulatory_action, deadline_days, correction_factor, reporting_fraction, source_type, and timestamp — ready for Guardian consumption.
Taxonomy
Linnaean classification joined from the algovigilance taxonomy index via the parent config's rank.
| Rank | Value |
|---|---|
| domain | Substrata |
| kingdom | Constructa |
| phylum | Configa |
| class | station-config |
| order | vigilance |
| family | mcp-tool-config |
Characteristics:
- substrate:
config - domain:
pv - lifecycle:
continuous - authority:
read - compounding:
producer - io:
agent-request→tool-response
Input schema
drugstringrequired — Drug name (e.g., metformin)eventstringrequired — Adverse event name (e.g., lactic acidosis)chain_outputobjectrequired — The final_output JSON object from a completed chain run (pv-signal-to-action or vehicle-full-cascade)
Example call
POST /api/mcp
Content-Type: application/json
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "station__vigilance__verdict-from-chain",
"arguments": {
"drug": "",
"event": "",
"chain_output": {}
}
}
}How to invoke from a client
From any MCP-aware client, add https://algovigilance.com/api/mcp as an MCP server, then call this tool by name. From a raw HTTP client, send the JSON-RPC body above to /api/mcp.
Agent-friendly formats
Working inside an AI assistant? Use the Copy for AI button at the top of this page (or view the raw Markdown) to paste a clean, token-budgeted version of this tool's contract into your conversation.
Related
- All tools (3062 live)
- /api/mcp — endpoint
- /AGENTS.md — agent guide
- /tools/vigilance__verdict-from-chain/raw.md — this page's Markdown twin