- 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.
Bander
The OpenClaw I’d actually give my parents
Nexovous
The Rails-like framework for making any storefront AI-agent-ready. Catalog, cart and checkout compiled into a signed, versioned UI bundle any agent can render live — with a human-…
Humanloopbench
Human-in-the-loop LLM Failure Detection & Benchmark Toolkit — Auto-flag LLM failures (hallucination, refusal, factual error) with LLM-as-Judge explanations. Confirm them in a revi…
Awesome Human Mcps
Curated list of MCP servers for AI-to-human task delegation: RentAHuman, HumanMCP, GoToHuman, DoorDash, Instacart, and more
Multi Agent Explain Lab
An interactive, no-code tour of how a multi-agent AI system really works: one refund, six layers, from orchestration to observability. See where LangGraph, CrewAI, AutoGen, and MC…
Techlab AI Portfolio
AI Engineering Portfolio — TechLab AI Framework: hybrid RAG, MCP servers, multi-agent pipeline, human-in-the-loop governance
Mini Erp
Safe AI operations agent demonstrating MCP tools, deterministic ERP workflows, approval gates, evaluations, and idempotent writes.
Rtrace Agent Reliability
R-TRACE: Stateful agent evaluation and release reliability with reproducible Windows GPU evidence.
AI Social Content Agent
Approval-gated AI social content agent: drafts posts, generates imagery, publishes only after human approval over Telegram. Generic, plug-and-play (any account/niche). FastMCP ser…
Humanforai Python
Python client and CLI for Human For AI — hire a verified human operator from your AI agent: verification, testing, review, data collection, physical-world tasks. pip install human…
Netflix Content Acquisition AI Coworker
AI coworker for streaming content acquisition — Claude Code skills for title scoring, ROI modeling, contract-risk detection & performance monitoring, with MCP tool/data servers, a…
FDE Agent Platform
Agents propose, humans dispose — three FDE agents over a Postgres knowledge graph with SQL-enforced human gates
Bureau
A hierarchy of AI agents that take real actions — shell, GitHub, email, purchases — behind an approval floor written in code, not configuration (Latch). Zero dependencies.
Heyski
native macOS notifications from your terminal — one command, one banner
Erp Lite MCP
A Model Context Protocol (MCP) server exposing ERP-style data (sales orders, inventory, purchase requisitions) to AI agents — with a real human-in-the-loop approval gate on write…
SsuAI
숭실대 공개·개인 데이터를 대시보드와 승인 기반 AI 작업으로 연결하는 비공식 캠퍼스 웹 애플리케이션
AI Trip Planner
Multi-agent travel planner built on LangGraph & MCP , supervisor routing, guardrails, human-in-the-loop approval
Openmetadata MCP Agent
LangGraph agent for OpenMetadata governance over MCP (data-ai-sdk): HITL-gated writes, server-side tool allowlisting, Pydantic-validated tool calls, bounded catalog-in-prompt, dri…
Supascribe Notes MCP
An ChatGPT app that validates and writes structured index cards for System Notes into Supabase.
Agent Action Runner
Agent-safe action and workflow runner for TypeScript backends.
Aip Python
Agent Identity Protocol Python Implementation
Agent Coding Harness
Arnes para agentes de IA con múltiples proveedores y modelos, ejecución segura en sandbox, memoria vectorial con Qdrant, HITL, skills, herramientas HTTP y MCP, observabilidad, gob…
Learn Temporal AI Agent
2026 企业级 AI Agent 落地指南 — Temporal Durable Execution × LLM（40 章中文教程）
Draft MCP Server
Review AI-generated drafts before they go anywhere. MCP server with local review UI.
Agentport
Make a long-lived agent portable: swap the model provider underneath it, swap the chat channel in front of it, and gate memory writes behind human approval.
Auto Fill Forms
Human-in-the-loop job-application autofill agent: Claude Code + Playwright MCP fill forms from your profile; you always click Submit.
AegisAgent
Zero-trust API firewall and security integrity layer for autonomous AI agents & Model Context Protocol (MCP) tool execution. Secure, TOCTOU-proof, fail-closed.
Barzel Central Gateway MCP Server
Enterprise Model Context Protocol governance gateway and MCP control plane for AI agent tool routing, identity-aware policy, risk scoring, approvals, routebooks, workflow simulati…
Agentic AI Workspace
Production-grade Agentic AI workspace using Next.js, FastAPI, LangGraph ReAct, and Model Context Protocol (MCP) tool orchestration.
Nightwatch
Incident console where the AI agent's tool surface follows severity — tools mount as things get worse, unmount when they're over, and a human holds the keys. Built for the WebMCP…
Fluxgit MCP Server
Let AI agents use Git safely over MCP: 23 read-only tools plus 11 write operations that run only after you approve the exact diff, risk and restore point in the desktop app. Apach…
Formloop
Generate rich UI forms on-the-fly from LLM agents. Let your agent ask humans complex questions visually instead of via chat.
HumanAIE
Human AI Eyes (pronounced Human-Eye) — shared browser for human-AI collaboration. Highlight-to-teach builds spatial memory for your AI agent.
Criterion Loom
Criterion Loom: meaning-first audit tools for Codex work—requirements, plans, diffs, and completion evidence via CLI, MCP, and a companion skill.
Human Slave MCP
MCP server that gives AI agents on-demand access to a human operator via web or telnet
Notesentry MCP
Local-first MIMIC-III clinical-notes assistant — local LLM (Ollama) + MCP tools + human-in-the-loop. Data stays on device.
Approvals MCP
An MCP approval gate for AI agents
Sentinel Clinical Triage Agent
A multi-agent clinical triage & escalation co-pilot that keeps the risk decision in deterministic code (NEWS2) and audits its own advice. Google ADK 2.0, MCP, Gemini, Cloud Run. R…
Humanforai.dev
A human endpoint for AI agents - and a WebMCP workspace where you and your agent hire a real human, together. Built for the WebMCP Challenge.
Fearch
Honest web search and page reading for AI agents — an MCP server and CLI that identify themselves truthfully, respect robots.txt, and hand bot-checks to a human in a visible brows…
Agent Of Record
A governed foundation for AI agents doing work a person signs their name to, built and operated in public accounting: durable memory, human-approved execution, behavioral learning…
Governed MCP Gateway
Governed Model Context Protocol (MCP) servers in Java AND Python: policy engine, human-in-the-loop approval for sensitive actions, and a hash-chained audit log.
Auditable Multi Agent Recommender
Auditable multi-agent recommender for cloud optimization. Orchestration beats single-shot frontier models on correctness (18/18 vs 3–4/18), with a fully replayable evidence trail.…
Planforge
Local-first control plane where Claude Code plans, a human approves, and Codex builds in verified Git worktrees.
Msdesk
Autonomous operational reporting agent built on TrueForge with custom Slack MCP (SSE), sandboxed Python analytics, and human-in-the-loop safety gates.
Alcuin
Intelligence, composed — an extensible platform for building and operating AI agents.
Orkis
An agentic AI platform for .NET: run autonomous agents under graduated supervision — durable pause/resume runs, Firecracker-sandboxed execution, persistent workspaces with a super…
Belay MCP
Transaction firewall for AI agents. Preview, govern, verify and rewind MCP and native tool calls with deterministic policies, human approvals and signed evidence.
Delegated Authority Webmcp
WebMCP operations console where a human delegates a bounded envelope of authority and the browser's registered tool surface is what enforces it. Revoke a capability and the tool s…
Agentruntime
Business-neutral Go agent runtime built on the OpenAI Responses API