run-flywheel-mirror
Self-observation gate for the brain flywheel. Takes brain health metrics and determines if the flywheel can see itself spinning. Checks implicit store health, verdict coverage (sigma), tracker integrity, and guardian responsiveness. GREEN = full self-observation, YELLOW = partial (degraded tools), RED = blind (cannot measure own state).
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
guardian_okbooleanrequired — Input parameter: guardian_okimplicit_healthybooleanrequired — Input parameter: implicit_healthyverdict_pctintegerrequired — Input parameter: verdict_pcttracker_okbooleanrequired — Input parameter: tracker_ok
Example call
POST /api/mcp
Content-Type: application/json
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "station__microgram__run-flywheel-mirror",
"arguments": {
"guardian_ok": false,
"implicit_healthy": false,
"verdict_pct": 0,
"tracker_ok": 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.
Related
- All tools (3062 live)
- /api/mcp — endpoint
- /AGENTS.md — agent guide
- /tools/microgram__run-flywheel-mirror/raw.md — this page's Markdown twin