MCP servers for human-in-the-loop

Open-source MCP server for comparing products and asking the buyer before purchase.

Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing

The execution safety layer for AI agents.

Brakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code and any MCP app.

GenPark AI Agent Skill - Human-in-the-loop (HIL) approval gate and execution interrupt controller with cryptographic review tokens and diff inspection.

GenPark AI Agent Skill - Human-in-the-loop (HIL) approval gate and execution interrupt controller with cryptographic review tokens and diff inspection.

Turn SOP, policy and regulatory documents into human-verified Open Knowledge Format (OKF) bundles — every claim carries its source span. Desktop app + CLI + MCP server.

Windows computer-use MCP server (26 tools) with a human-in-the-loop approval gate: physical-input-only dialogs, signed guard switches, deny/launch lists, hash-chained audit log. 70+ unit tests, green

Open-source AI coworkers for your team. They do recurring work, ask before risky steps, and show you exactly what they did.

A QuickBooks MCP server built for real books. Exposes QuickBooks Online as callable tools over the Model Context Protocol, with every create, update and delete gated behind human approval and a plain-

Render agent-written Markdown as a live local page, and send the human's click back to the agent as typed data. Human-in-the-loop approval gates for coding agents.

Multiplayer browser sessions for developers and AI coding agents

Community-built Codex–COMSOL bridge using officially supported MATLAB MCP and LiveLink integration layers, with native multiphysics API access, task-level execution, same-model Desktop observation, an

MCP server for market data, SEC filings, macro and risk tooling across Webull, Saxo and IBKR — with order execution behind a human approval step the assistant cannot reach. 41 tools, filtered to what

Executable AI agent readiness gate: GitHub Action, prompt injection evals, LangGraph traces, risk profiles, and bilingual EN/中文 docs.

Lightweight browser-side AI agent framework for legacy enterprise web apps—Java 8, Spring Boot 2, TypeScript, MCP/WebMCP, OpenAI-compatible LLMs, tool calling, streaming, audit, and persistence. 面向存量企

Local-first AI brain for personal relationships and communication, powered by MCP｜多平台身份图谱、关系记忆、回复策略与受控自动回复

MealPR — Code Review for Your Meal. Turns McDonald's MCP ordering into a reviewable, human-approved agent workflow.