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

hitl-submit

station__agent-intel__hitl-submit external (needs EXECUTION_BACKEND_URL) agent-intel non-pv Constructa Configa

by risk level and score. Each entry has an expiration (default 72 hours).

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	`agent`
family	`mcp-tool-config`

Characteristics:

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

Input schema

assign_to string
evidence any
expires_hours integer
recommendation stringrequired — Recommended action (e.g., "investigate", "restrict_access", "emergency_withdrawal")
risk_level stringrequired — Risk level: "low", "medium", "high", "critical"
risk_score numberrequired — Risk score (0.0 - 10.0)
target stringrequired — Target entity (e.g., drug name, signal ID)
tool stringrequired — Source tool that generated the decision (e.g., "guardian_evaluate_pv")

Example call

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__agent-intel__hitl-submit",
    "arguments": {
      "recommendation": "",
      "risk_level": "",
      "risk_score": 0,
      "target": "",
      "tool": ""
    }
  }
}

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/agent-intel__hitl-submit/raw.md — this page's Markdown twin