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

Microgram: smm-violation-classifier

station__algovigilance__microgram-smm-violation-classifier native (always callable) algovigilance pv-core Constructa Configa

NVG-SMM-001 Section 4: Classify epistemological violations by severity (F/C/M/m). Chemistry analog: activation energy tiers — Fatal is an insurmountable barrier, minor is thermal noise.

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

post_hoc_endpoint booleanrequired — Input variable post_hoc_endpoint
suppressed_hypothesis booleanrequired — Input variable suppressed_hypothesis
fabricated_data booleanrequired — Input variable fabricated_data
undocumented_deviation booleanrequired — Input variable undocumented_deviation
post_hoc_analysis_criteria booleanrequired — Input variable post_hoc_analysis_criteria
missing_negative_results booleanrequired — Input variable missing_negative_results
undisclosed_coi booleanrequired — Input variable undisclosed_coi
criterion_drift booleanrequired — Input variable criterion_drift
uses_proves_confirms booleanrequired — Input variable uses_proves_confirms
missing_power_calculation booleanrequired — Input variable missing_power_calculation
imprecise_significant booleanrequired — Input variable imprecise_significant
has_minor_deficiency booleanrequired — Input variable has_minor_deficiency

Example call

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__algovigilance__microgram-smm-violation-classifier",
    "arguments": {
      "post_hoc_endpoint": false,
      "suppressed_hypothesis": false,
      "fabricated_data": false,
      "undocumented_deviation": false,
      "post_hoc_analysis_criteria": false,
      "missing_negative_results": false,
      "undisclosed_coi": false,
      "criterion_drift": false,
      "uses_proves_confirms": false,
      "missing_power_calculation": false,
      "imprecise_significant": false,
      "has_minor_deficiency": 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 (7718 live)
/api/mcp — endpoint
/AGENTS.md — agent guide
/tools/algovigilance__microgram-smm-violation-classifier/raw.md — this page's Markdown twin