Microgram: perturbation-layer-classifier
Classifies pharmacovigilance observations into the 6-layer perturbation pattern model. Given evidence characteristics, identifies which mechanistic layer(s) the observation represents — from molecular binding (L1) through systemic feedback (L6). Exercises μ (Mapping) — each observation maps to its mechanistic origin.
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 | algovigilance |
| family | mcp-tool-config |
Characteristics:
- substrate:
config - domain:
pv - lifecycle:
continuous - authority:
read - compounding:
producer - io:
agent-request→tool-response
Input schema
is_binding_databoolean — Input variable is_binding_datais_functional_assayboolean — Input variable is_functional_assayis_pathway_levelboolean — Input variable is_pathway_levelis_cellular_responseboolean — Input variable is_cellular_responseis_organ_manifestationboolean — Input variable is_organ_manifestationis_systemic_feedbackboolean — Input variable is_systemic_feedbackevidence_sourcestringrequired — Input variable evidence_sourcehas_mechanistic_detailboolean — Input variable has_mechanistic_detail
Example call
POST /api/mcp
Content-Type: application/json
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "station__algovigilance__microgram-perturbation-layer-classifier",
"arguments": {
"evidence_source": ""
}
}
}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 (7718 live)
- /api/mcp — endpoint
- /AGENTS.md — agent guide
- /tools/algovigilance__microgram-perturbation-layer-classifier/raw.md — this page's Markdown twin