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.
- Collectionobserved · static extractionOpen-source Claude Code skills for SEO, GEO, Google Ads, Meta Ads
- MCP serverobserved · static extractionHSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.
- MCP serverobserved · static extractionTask spine + dead-end search + approvals for AI coding agents (Claude Code, Cursor, Cline, Continue.dev, Zed). Past dead ends are semantical
- MCP serverobserved · static extractionTrust Graduation gate: Claude can do real work once Mission decides what it is allowed to do.
- MCP serverobserved · static extractionLoopPause MCP server — pause agent execution and route human approval requests
- MCP serverobserved · static extractionBudget & cost control for AI agents — per-agent spend caps + rate limits before each call.
- MCP serverobserved · static extractionGate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.
- MCP serverobserved · static extractionHosted OAuth MCP for Google, Meta, X, and LinkedIn Ads, GA4, and Search Console.
- MCP serverobserved · static extractionSupraWall security gateway for AI agents. Provides deterministic guardrails for MCP agents.