Human approval MCP servers

Neutral tie-breaks between AI agents and sealed review of an agent's output, with signed receipts.

Make AI apps answer your way, check with you before acting, and get approvals on your phone.

Human in the loop for AI agents: ask ID verified people to check a decision before acting.

MCP proxy: holds risky tool calls for passkey approval; signed receipts you can check offline.

Needs the PrivacyFence app from privacyfence.eu: human approval and audit for AI access to your data

Founders' AI COO: every AI cofounder's Routines on time — heartbeat, failures, approvals, reports.

Baselines an MCP server's tools and detects tool-definition changes after approval

Notify people through Cue: preferences, attention budgets, quiet hours and approval apply.

Startup cap table: ownership, SAFEs, vesting and round modeling, plus drafts for admin approval.

Audit trail and traceability for AI agents. MCP gate: evaluate, ingest, request approval.

Manage vacation rentals, bookings, calendars and operations with OAuth and action approvals.

Human approval gate for AI agents: risk-scored requests that only a person can approve

Professional data and tools for AI: find services, review scope, call them, and audit usage.

Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.

Native WebKit for Mac. Human approval and persistent sign-ins. Requires the companion app.

Clean up talk recordings: find redos, retakes and dead air, review every cut, render and verify.

RevRule by Payload: read entitlement graphs, review payout evidence, dry-run revenue events.

Capture local agent traces and inspect failures, approvals, and run comparisons.

Set up human approval for your AI agents' tool calls.

Read local agent-run JSONL traces through MCP for failures, approvals, and run comparisons.

Local Phocinae decision-engine MCP stdio server: fail-closed approval gate + classify/route/score.

Run shell commands on remote computers with optional per-command approval, using only curl and bash.

Exact-action approval for consequential agent actions: request, track, and verify signed receipts.

AI BVF: review AI proposals with Stop, Fix or Accelerate, evidence gaps and next actions.

Approval and budget checks before agent spending or tool use. Cooperative MCP; host must ask.

Privileged command execution proxy with human approval via pkexec or sudo

Access control for AI agents and MCP servers: allow, hold for approval, or block each tool call

Baselines an MCP server's tools and detects tool-definition changes after approval

Ask a human before your agent acts: approval requests decided on a phone.

Answer CTRLRun approvals from an MCP client: list what is held, inspect it, grant or deny.

Tracks U.S. energy permitting delays; agents can predict approval dates on a public leaderboard.

Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.

Human approval for AI agents: a named person approves or rejects, silence is not consent.

Authorization layer between AI agents and money: ALLOW/APPROVAL/DENY, budgets, audit.

Spend approval gate for AI agents: budget caps, HITL thresholds, signed audit hash.

Give your AI agent a spending limit: approval controls and single-use virtual cards.

Read your TacticalRMM fleet; run commands only after per-command human approval.

Discover funded agent work and prepare approval-gated TaskMarket delegations.

logi Agent Approval Gate — human approval on the phone before high-risk agent actions.

Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.

Unofficial SberBank Online: read accounts and operations, transfer with human approval.

Turns your Prisma schema into typed MCP tools, with destructive writes gated behind human approval

A local receipt and approval gate for AI agent sessions. The agent can act, but it cannot sign.

Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.

MCP server for Veeam Backup for Microsoft 365: read-only review + gated, audited restore tier.

Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve.

Inspect Tidebase agent runs, resolve approval gates, and trigger recovery from your AI assistant.

EVM contract/token risk check + ERC20 approval (proxy, EIP-7702, unlimited-allowance). Zero deps.

Secure secret management with a Human-In-The-Loop (HITL) interceptor for agent mutations.