request_approval

9 registry entries were observed exposing a tool named request_approval — none of them flagged as a privileged capability.

Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 8,470 of 26,658 scannable entries (32%) — an entry that has not been scanned cannot appear here, so absence from this list is not evidence that an entry does not expose this tool.

  1. trust 60/100 · BCollectionobserved · static extraction
    Open-source Claude Code skills for SEO, GEO, Google Ads, Meta Ads
  2. trust 60/100 · BMCP serverobserved · static extraction
    HSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.
  3. trust 60/100 · BMCP serverobserved · static extraction
    Task spine + dead-end search + approvals for AI coding agents (Claude Code, Cursor, Cline, Continue.dev, Zed). Past dead ends are semantical
  4. trust 60/100 · BMCP serverobserved · static extraction
    Trust Graduation gate: Claude can do real work once Mission decides what it is allowed to do.
  5. trust 60/100 · BMCP serverobserved · static extraction
    LoopPause MCP server — pause agent execution and route human approval requests
  6. trust 60/100 · BMCP serverobserved · static extraction
    Budget & cost control for AI agents — per-agent spend caps + rate limits before each call.
  7. trust 60/100 · BMCP serverobserved · static extraction
    Gate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.
  8. trust 60/100 · BMCP serverobserved · static extraction
    Hosted OAuth MCP for Google, Meta, X, and LinkedIn Ads, GA4, and Search Console.
  9. trust 60/100 · BMCP serverobserved · static extraction
    SupraWall security gateway for AI agents. Provides deterministic guardrails for MCP agents.

All indexed toolsSearch the registry for request_approval