Do Not Act

Fail-closed MCP guard for prediction-market agents: dispute risk, preflight decisions, signed receipts, token-risk and x402.

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключениемРаботаетБез входаГлобальныйБесплатноТолько чтение

Что умеет

  • Donotact Preflight: Default prediction-market decision-boundary check. Pass requested action context when available so DoNotAct can evaluate resolver_type, decision, size-vs-book capacity, evidence_se
  • Donotact Preflight Token: Run DoNotAct token-risk preflight using the GoPlus T1-T8 fail-closed taxonomy. Authenticated MCP calls use DONOTACT_API_KEY; accountless agents can use the x402 token preflig
  • Donotact Resolution Risk: Run DoNotAct resolution-governance and ambiguity diagnostics for a venue market. Diagnostics only. DoNotAct is fail-closed: if the verdict is DO_NOT_ACT or INSUFFICIENT_EVIDE

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

Fail-closed MCP guard for prediction-market agents: dispute risk, preflight decisions, signed receipts, token-risk and x402.

Список инструментов сервера (7)

Технические названия из tools/list. Нужны только разработчикам.

donotact_preflightDefault prediction-market decision-boundary check. Pass requested action context when available so DoNotAct can evaluate resolver_type, decision, size-vs-book capacity, evidence_set, and safe operating limits. Diagnostics only. DoNotAct is fail-closed: if the verdict is DO_NOT_ACT or INSUFFICIENT_EVIDENCE, do not proceed. This is operational diagnostics, not financial advice.
donotact_preflight_tokenRun DoNotAct token-risk preflight using the GoPlus T1-T8 fail-closed taxonomy. Authenticated MCP calls use DONOTACT_API_KEY; accountless agents can use the x402 token preflight route documented in llms.txt. Diagnostics only. DoNotAct is fail-closed: if the verdict is DO_NOT_ACT or INSUFFICIENT_EVIDENCE, do not proceed. This is operational diagnostics, not financial advice.
donotact_resolution_riskRun DoNotAct resolution-governance and ambiguity diagnostics for a venue market. Diagnostics only. DoNotAct is fail-closed: if the verdict is DO_NOT_ACT or INSUFFICIENT_EVIDENCE, do not proceed. This is operational diagnostics, not financial advice.
donotact_disputeRun DoNotAct dispute lifecycle diagnostics where public lifecycle evidence is covered. Early-warning only. Treat uma_dispute_detected and uma_dispute_already_active as blocking unless a human operator explicitly overrides outside DoNotAct. No execution, custody, signing, routing, or advice.
donotact_watchlist_addAdd or update a DoNotAct early-warning watchlist item. Early-warning only. Treat uma_dispute_detected and uma_dispute_already_active as blocking unless a human operator explicitly overrides outside DoNotAct. No execution, custody, signing, routing, or advice.
donotact_alertsRead the DoNotAct alert feed for the authenticated API key. Early-warning only. Treat uma_dispute_detected and uma_dispute_already_active as blocking unless a human operator explicitly overrides outside DoNotAct. No execution, custody, signing, routing, or advice.
donotact_dispute_history_csvFetch the paid dispute-history CSV export for the authenticated API key. The CSV is sourced from the dispute ledger and carries no ROI, alpha, or avoided-loss claim. Diagnostics only. DoNotAct is fail-closed: if the verdict is DO_NOT_ACT or INSUFFICIENT_EVIDENCE, do not proceed. This is operational diagnostics, not financial advice.
Do Not Act: подключить к Claude, ChatGPT, Cursor · Connectors.fun