← home · ← tools · View as Markdown (.md) · JSON

run-perturbation-layer-classifier

station__microgram__run-perturbation-layer-classifier external (needs EXECUTION_BACKEND_URL) microgram pv-core Constructa Configa

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	`microgram`
family	`mcp-tool-config`

Characteristics:

substrate: config
domain: pv
lifecycle: continuous
authority: read
compounding: producer
io: agent-request → tool-response

Input schema

is_pathway_level booleanrequired — Input parameter: is_pathway_level
has_mechanistic_detail booleanrequired — Input parameter: has_mechanistic_detail
is_organ_manifestation booleanrequired — Input parameter: is_organ_manifestation
is_functional_assay booleanrequired — Input parameter: is_functional_assay
is_systemic_feedback booleanrequired — Input parameter: is_systemic_feedback
evidence_source stringrequired — Input parameter: evidence_source
is_cellular_response booleanrequired — Input parameter: is_cellular_response
is_binding_data booleanrequired — Input parameter: is_binding_data

Example call

POST /api/mcp
Content-Type: application/json

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__microgram__run-perturbation-layer-classifier",
    "arguments": {
      "is_pathway_level": false,
      "has_mechanistic_detail": false,
      "is_organ_manifestation": false,
      "is_functional_assay": false,
      "is_systemic_feedback": false,
      "evidence_source": "",
      "is_cellular_response": false,
      "is_binding_data": false
    }
  }
}

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.

All tools (3062 live)
/api/mcp — endpoint
/AGENTS.md — agent guide
/tools/microgram__run-perturbation-layer-classifier/raw.md — this page's Markdown twin