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

protective-depth

station__tov-proofs__protective-depth external (needs EXECUTION_BACKEND_URL) tov-proofs pv-core Constructa Configa

Compute minimum protective depth H such that ℙ(H) < target_probability. Formula: H ≥ 1 + log(1/ε)/α. Answers: 'how many safety layers do I need?'

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	`tov`
family	`mcp-tool-config`

Characteristics:

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

Input schema

target_probability numberrequired — Target probability threshold ε, in (0, 1). Example: 0.05 for 5% residual risk
attenuation_rate numberrequired — Attenuation rate α (must be positive)

Example call

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__tov-proofs__protective-depth",
    "arguments": {
      "target_probability": 0,
      "attenuation_rate": 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/tov-proofs__protective-depth/raw.md — this page's Markdown twin