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

run-loop-cascade

station__microgram__run-loop-cascade external (needs EXECUTION_BACKEND_URL) microgram pv-core Constructa Configa

Flywheel loop interaction hierarchy (Spec Section 4). Cascade: 5→1→2→4, with 3→2. Takes all 5 loop outputs and applies dependency rules to produce system-level verdict. NOMINAL (all healthy), DEGRADED (warnings present), CASCADING (failure propagating through dependency chain), COLLAPSED (2+ loops failed).

Taxonomy

Linnaean classification joined from the algovigilance taxonomy index via the parent config's rank.

Characteristics:

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

Input schema

• l1_state stringrequired — Input parameter: l1_state
• l5_state stringrequired — Input parameter: l5_state
• l3_class stringrequired — Input parameter: l3_class
• l4_state stringrequired — Input parameter: l4_state
• l2_above_critical integerrequired — Input parameter: l2_above_critical

Example call Copy code

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__microgram__run-loop-cascade",
    "arguments": {
      "l1_state": "",
      "l5_state": "",
      "l3_class": "",
      "l4_state": "",
      "l2_above_critical": 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.

Related

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