Do Not Act

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

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • 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

What data it sees

Do you need an account

No: the server works without sign-in

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

How to connect

How to connect Do Not Act to Claude

The server address to paste into Claude settings:

https://donotact--aionathenea.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Do Not Act to ChatGPT

The server address to paste into ChatGPT settings:

https://donotact--aionathenea.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Do Not Act to Cursor

The server address to paste into Cursor settings:

https://donotact--aionathenea.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (7)

Raw names from tools/list. Only developers need these.

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.