- Conduid
- Marketplace
- #human-in-the-loop
MCP servers tagged human-in-the-loop
489 live MCP servers tagged "human-in-the-loop", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with human-in-the-loop.
Jv Obsidian Assistant
Portfolio extract of a persona-driven AI assistant over an Obsidian Markdown vault through a typed MCP filesystem core. The private original runs daily; this sanitized cut reads b…
Procurepilot
以Openclaw架构思想构建的基于Deep Agents、MCP、OpenSandbox、FastAPI 与 Vue 3 的多用户智能采购协作平台，支持多 Agent 编排、异步任务、SSE 流式交互、HITL 审批、Opensandbox沙箱隔离与 ERP 数据分析。
Agentic Plugins Toolkit
🧩 agentic-plugins-toolkit · 📦 6 plugins agénticos para Claude Code, OpenAI/Codex, Copilot, Gemini y MCP · 🧭 repository-engineering · 🏗️ legacy-modernization · 🎓 learning-program-s…
Langgraph Loan Triage
Loan review demo built with LangGraph. Triage, risk review, human sign off, and an audit record for every step.
Auto Apply Agent
Human-reviewed browser agent harness using Trackly MCP, Codex computer use, state-bound approval, and fail-closed recovery.
Groundstation
Agentic mission-ops copilot for the Heliosnet ground system: LangGraph multi-agent orchestration over MCP tools, RAG-cited playbooks, tiered model routing, and a trained anomaly-t…
TensorNode
AI Executive Assistant that transforms messages into decisions using a governance-first multi-agent architecture built with Google ADK and Gemini.
Personal AI Employee Hackathon 0
An autonomous, local-first Digital FTE built for the Personal AI Employee Hackathon. It leverages Claude Code, Obsidian, and the Model Context Protocol (MCP) for a complete human-…
Konect4ai Webmcp
Agents propose, humans approve. A WebMCP workspace where an agent can request a new data capability but only the page owner can grant it — and when it asks a question, the answer…
Google MCP Multi Account
Multi-account Google Workspace (Gmail, Drive) for LLM agents — 100% local, default-deny policy, human-in-the-loop access. A macOS MCP server.
Medsguard Agent
An LLM-driven medication-logging agent with a deterministic safety spine.
Agentcloud
Governed persistent AI workers with default-deny authority, human approvals, dry-runs, and an authenticated MCP.
Secure Files Organizer MCP
إدارة وتنظيم آمن للملفات عبر خادم MCP مع تأكيد الحذف البشري | A secure local MCP server for file triage, organization, and human-in-the-loop safe deletions.
Docintel MCP
Document Intelligence MCP server: extraction, confidence-threshold routing, human review queue, and BM25 search over the Model Context Protocol
Rentahuman MCP
MCP server for RentAHuman (workman.rent) — let an AI agent hire an identity-verified person for a short real-world task. Non-custodial split payment, no escrow, audit per dispatch…
Ax Hackathon 2026
AX hackathon project workspace for designing, implementing, and validating multi-agent AI solutions.
BebVibe Web Control
Auditable web automation layer for AI agents using deterministic workflows and MCP.
Decision Memory Control Plane
Local-first control plane for evidence-linked decision memory, governed tasks, deterministic evals, and human-approved actions.
LongTable
Research control plane for AI-assisted scholarship: durable human checkpoints, lawful evidence provenance, and verifiable research packages.
Theokit
The full-stack TypeScript framework for AI agents. An agent is a file: drop it in agents/ and it gets an HTTP route, token streaming, human-in-the-loop approvals and a typed clien…
Cheers
A Slack-style hub for humans and AI agents — real-time channels, external agent bots, file-aware chat, and channel memory. Open-source & self-hostable & MacOS & IOS.
CellTypePilot
Agent-native, local-first plugin for auditable single-cell annotation with governed evidence, contrastive review, conservative abstention, and human-reviewed draft outputs.
AgenticAI OnRamp With Langgraph
Branch-based learning repo for Agentic AI and LLM engineering with LangGraph: ReAct tool calling, Agentic RAG, MCP, Reflection, Reflexion, Human-in-the-loop memory, and DeepAgents…
Graphagents
Agents with LangGraph
DevdocxAI
DevDocxAI is a production-grade multi-agent AI system that automatically generates, maintains, and updates engineering documentation by deeply understanding you…DevDocAI is a prod…
Polaxis SDK MCP
Python SDK and MCP server for Polaxis - AI agent governance platform. Evaluate every tool call against policies in real time: block dangerous actions, enforce budgets, route to hu…
Agentic AI Overview
Hands-on catalog of 15 agentic AI design patterns with runnable LangGraph examples. Same 3 scenarios (IT helpdesk, e-commerce, ML pipeline) across all patterns. OpenAI & DeepSeek,…
Release Gate
Human-in-the-loop AI release gate: Gemini 3 on Vertex AI reasons over Arize Phoenix telemetry to approve, block, or guardrail a version promotion, with idempotent gated writes. Go…
Verification Security
Public verification, security review, and skill quality process for Agent Skill Exchange
Maqam
Give AI agents hands without handing them the keys: exact one-use approvals and verifiable receipts for registered actions.
Flag MCP
When your AI assistant hits a crossroads, instead of guessing and potentially wasting your time, it pauses — presenting you with meaningful choices, like dialogue options in a gam…
HITL KIT
@hitl-kit/* — React primitives, Zod event schemas, composable decision gates, and LangGraph / AI-SDK / MCP adapters for human-in-the-loop agentic UIs. Components install via the s…
Toolbraid
A browser-native semantic and policy control plane for safe, explainable, human-approved WebMCP execution across sites.
TGS 2025054471 Autonomous AI Agents
WSQ Autonomous AI Agents (TGS-2025054471): 2-day visual courseware with 18 hands-on Hermes Agent and OpenClaw labs.
Sokkan
The helm, not the autopilot — self-hosted cockpit for parallel Claude Code sessions, with your project memory auto-injected at spawn.
Turnkeeper Js
Public Turnkeeper SDK, CLI, MCP server, agent-builder skill, and governed-agent examples.
Bump
Serverless E2E mail for AI agents, with a human gate. SLOW DOWN — HUMAN AHEAD.
Bailinghub Dsh Plugin
让本地 DeepSeek Harness Agent 查询和操作你的商城、SaaS 或其他业务后台，原有权限与审计仍由 BailingHub 管理。Independent DSH integration for BailingHub.
Stageflow
Configurable, typed multi-stage agent workflows for Pi — local console, human gates, MCP, and CI.
ZpAgent
ZpAgent - ReAct Agent (ChatBot)Project Built with LangChain 1.2 + LangGraph + FastAPI + Vue 3, this is a ReAct-paradigm intelligent agent that supports SSE streaming output, dynam…
WatchDock
Review-first AI-assisted file organizer with durable approvals for Windows, macOS, and Linux.
Agentic AI Environment
AI Workforce of the Future - Research Environment
Across Agents Assistant
Local-first macOS control room for supervised engineering loops across coding agents.
Rapid Agent Guardian
Agent safety gate for real work: evidence envelopes, human approval checkpoints and release guardrails for AI app builders.
Agent Code Buddy
Companion approval surface for local coding agents
Page Agent SDK
给网页一个会改页面的 AI 助手。一行代码挂载对话框，AI 通过工具按 schema 安全读写页面数据，实现「对话式」搭建/编辑/运维。
Merakicore
Continuous learning for AI: evidence-backed corrections, scoped guidance, evaluation, and rollback.
AgentTrustOps
Side-effect governance, approvals, crash-safe idempotency, reconciliation, and audit for AI agents.
NexusAIAgentFramework
Durable, auditable AI agent runtime with human approval gates, budgets, replay, MCP support and the Open Agent Run format.
Prfrail
Provable rails for unattended AI engineering — every code change, gate, evidence and rollback is auditable. / ProofRail 为 AI 无人值守编程铺设可证明的轨道——代码变更、门禁、证据、回滚，全程可审计。