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

run-sota-authority-decompose

station__microgram__run-sota-authority-decompose external (needs EXECUTION_BACKEND_URL) microgram pv-core Constructa Configa

Decompose threshold authority into primitives — consensus breadth, credential strength, evidence basis, institutional backing — and score defensibility. Detects Takeda-pattern authority assertions (claims without defensible criteria). Returns authority class (SOVEREIGN/ESTABLISHED/EMERGING/CONTESTED/LONE/UNGROUNDED/ASSERTION), defensibility rating, vulnerability analysis, and recommendation.

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

consensus_level integerrequired — Breadth of agreement: 1=single author, 2=research group, 3=professional society, 4=multi-society, 5=international harmonization (ICH/WHO)
credential_strength integerrequired — Credentialing depth: 1=self-declared, 2=peer-recognized, 3=board-certified, 4=regulatory-designated, 5=statutory mandate
evidence_basis integerrequired — Evidence grounding: 1=assertion only, 2=case-based, 3=empirical study, 4=validated framework, 5=replicated multi-site
institutional_backing integerrequired — Institutional power: 1=individual, 2=academic dept, 3=professional body, 4=national regulator, 5=supranational (WHO/ICH/EMA)

Example call

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__microgram__run-sota-authority-decompose",
    "arguments": {
      "consensus_level": 0,
      "credential_strength": 0,
      "evidence_basis": 0,
      "institutional_backing": 0
    }
  }
}

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-sota-authority-decompose/raw.md — this page's Markdown twin