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

assess-naranjo

station__pv-engine__assess-naranjo external (needs EXECUTION_BACKEND_URL) pv-engine pv-core Constructa Configa

Run the Naranjo Adverse Drug Reaction Probability Scale. Scores 10 questions about temporal relationship, dechallenge, rechallenge, alternative causes, dose-response, and objective evidence. Returns total score (range -4 to +13) and category: Definite (>=9), Probable (5-8), Possible (1-4), Doubtful (<=0). Reference: Naranjo et al. (1981) Clin Pharmacol Ther 30:239-245.

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	`guardian`
family	`mcp-tool-config`

Characteristics:

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

Input schema

drug string — Suspected drug name
event string — Adverse event term
q1_previous_reports stringrequired — Previous conclusive reports on this reaction? (yes/no/unknown)
q2_temporal_relationship stringrequired — Event appeared after suspected drug was given? (yes/no/unknown)
q3_dechallenge stringrequired — ADR improved when drug was discontinued? (yes/no/unknown)
q4_rechallenge stringrequired — ADR reappeared when drug was readministered? (yes/no/unknown)
q5_alternative_causes stringrequired — Alternative causes could explain the reaction? (yes/no/unknown)
q6_placebo_response stringrequired — Reaction appeared when placebo was given? (yes/no/unknown)
q7_drug_concentration stringrequired — Drug detected in blood in toxic concentration? (yes/no/unknown)
q8_dose_response stringrequired — Reaction more severe with increased dose? (yes/no/unknown)
q9_previous_experience stringrequired — Patient had similar reaction to same or similar drugs? (yes/no/unknown)
q10_objective_evidence stringrequired — ADR confirmed by objective evidence? (yes/no/unknown)

Example call

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__pv-engine__assess-naranjo",
    "arguments": {
      "q1_previous_reports": "",
      "q2_temporal_relationship": "",
      "q3_dechallenge": "",
      "q4_rechallenge": "",
      "q5_alternative_causes": "",
      "q6_placebo_response": "",
      "q7_drug_concentration": "",
      "q8_dose_response": "",
      "q9_previous_experience": "",
      "q10_objective_evidence": ""
    }
  }
}

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 (3059 live)
/api/mcp — endpoint
/AGENTS.md — agent guide
/tools/pv-engine__assess-naranjo/raw.md — this page's Markdown twin