- 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.
Lore Oss
Agent-driven, human-in-the-loop knowledge base: AI agents extract business rules from code via MCP, reviewers approve/reject in a web UI, and rejected rules feed back to refine —…
Ingest API
FastAPI-based multi-agent orchestrator for Odoo. Uses a Semantic Router to dispatch intents to specialized agents via Model Context Protocol (MCP/FastMCP). Features Guardrails AI…
Cx Orchestrator
Unofficial local-first Codex plugin for Human-approved CX1-to-CX2 task orchestration through MCP.
Agentweaver
Run an AI agent on a task inside a sandboxed git worktree, stream every step live, and gate merges behind human review — .NET + React, AKS-ready, with an MCP server.
EPICS MCP
Ask an AI assistant about your EPICS control system: live PV values, why a PV is disconnected, and where it appears across ChannelFinder, the Archiver and the alarm tree. Read-onl…
Claude Redline
An interactive Human-in-the-Loop (HITL) review tool for Claude. Opens a local UI to 'redline' specifications and plans before code is written.
QuantMinds
QuantMinds Hackathon - RAG Pipeline
Forum
Coordinate agent fleets: routing, quality checks, prose contracts, and a replayable hash-chained ledger that preserves plans, evidence, results, and resumable handoffs. Model-agno…
Litagatoro
️ Litagatoro: The Premium Human-in-the-Loop Voice Oracle for AI Agents. Enables AI to hire real humans for voice tasks (verifications, acting, identity checks) on the Polygon…
Tether Md
Anchored comments for Markdown. You comment, the agent proposes, you decide. Byte-identical clean export.
Codex Bridge MCP
连接 Claude 与 Codex 的本地 MCP：让复杂开发任务持续执行、可恢复、可审阅
Sideguard
MCP guard & vibe coding security tool for Cursor and Claude Code. Fail-closed human-in-the-loop approval for shell commands and MCP tools—local daemon, YAML policy, no cloud.
Intent Gate Service
DingTalk sister MCP service of intent-gate: group consensus channel + blocking human-decision gates for requirement intent alignment. Optional — the main plugin closes the loop al…
BandhanAI
Boost your e-commerce with BandhanAI, an AI-driven CRM agent for smart customer analytics and automated marketing. 🤖📊 Streamline your customer engagement today!
Ai2hum.ai
Human API for AI agents — route physical tasks to KYC-verified humans in India. MCP server, REST API, Python SDK.
Over The Top MCP
Human vs AI Connect 4 over MCP — the agent persists across turns until game over, no polling, no restart
Hospitality Multi Agent Architecture
Multi-agent AI system for hotel operations: F&B forecasting, guest memory, environmental risk. MCP-native, FastAPI, WhatsApp delivery, evals as CI merge gates.
QMesha
MCP-native agent middleware with governance enforced in code: spending limits that refuse before execution, auditable decision provenance, and local-first Markdown memory.
Maps Browser MCP
Google Maps MCP server for bounded browser automation with optional Human takeover through a dedicated Chrome session.
Ctrlrun
The execution safety layer for AI agents.
AI Approval Queue
Personal assistant add-on scans sources (email, texts, finance, etc) and recommends a queue of cards with scripted follow-up actions.
Cc Plan Review
MCP server for human review of Claude-generated plans with web UI
Push Bridge
Approve your AI coding agent's risky commands from your phone — Claude Code hook + MCP (Codex/Gemini/Cursor).
Role Scout
Agentic job search pipeline: LangGraph + HiTL review + Claude scoring + resume tailoring + MCP server
Capability Atlas
Decide what to reuse instead of rebuild — local-first research intelligence, operated by agents, governed by you.
Iridium Linkedin Agent
Iridium - LinkedIn MCP for AI Agents
Issa
Issa — Intelligence Server-Side Agent. Issa: An open-source Action-Control Gateway to stop AI agents from executing unauthorized side-effects.
FastHands
Local-first cross-platform execution and research layer for AI agents with durable checkpoints and operator control.
Careerops Automation MCP Hub
Secure MCP and automation hub for CareerOps, integrating n8n and OpenClaw with durable workflows, human review, PostgreSQL and an AI Agent Engine
Briefing
Paced browser briefings for coding agents: CLI, MCP server, hub
Codex Comsol Bridge
Community-built Codex–COMSOL bridge using officially supported MATLAB MCP and LiveLink integration layers, with native multiphysics API access, task-level execution, same-model De…
Yance
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
DiscordClaudeCode
Discord x Claude Code bridge via MCP (Model Context Protocol). Human-in-the-loop AI assistant integration with forum threads, real-time communication, and AI-powered title generat…
AILIENANT
Ailienant is a structured engineering agentic OS for VS Code. No vibe coding or unauditable black boxes. Built for engineers demanding total control. We provide a live codebase kn…
Braid
A harness framework that keeps AI and your team building one domain model together, in a loop where the AI drafts and asks, and people decide.
Synapsor Runner
Let AI agents query and update Postgres/MySQL without raw SQL, unrestricted schema access, or database credentials in the model; writes stay reviewed.
X1 Agent Skills
Your family office just hired an agent. Open-source skills that give AI agents real financial work, durable X1 context, and a hard stop before money moves.
Autoagent
Zero-dependency LLM agent runtime — tool use, MCP, sandboxed self-written tools, checkpoint/resume, approval gates, bi-temporal fact memory, code-level guards (context bounds, loo…
Confirm MCP
MCP server for human approvals. Any MCP agent gets a request_approval tool: pause on risky actions, a human approves or edits, then resume.
NFTY MCP
MCP server for ntfy.sh notifications, asynchronous agent messaging, and human-in-the-loop workflows.
AutoDS Copilot
A no code AI data science copilot. Point it at a spreadsheet and it runs the whole machine learning workflow, then explains the result in plain language. Built with scikit learn,…
Praxa
Open-source TypeScript SDK, CLI, and MCP contracts for governed AI agents and the Praxa agentic harness.
Sessionbridge
Human-in-the-loop browser sessions for MCP clients using Playwright and Chrome DevTools Protocol.
LNSAT
Open-source, pre-release source for policy-governed AI-agent authorization, scoped human approval, audit evidence, and read-only MCP adapters.
Mooting
Claude Code, Codex and Copilot in one shared council — CLI coding agents debate over MCP, and a human rules every decision. Terminal UI, no API keys.
Nomos Browser
Navegação governada para agentes de IA, com a Gi num painel lateral que abre já conectado (um clique, sem token). ASK/AUTO com aprovação amarrada à ação, console ao vivo, trilha a…
Sollu
A voice assistant that turns your voice notes into real tasks and actions, while keeping you in control of important decisions.
Veriremit
Source-grounded AI agent for vendor payment verification, deterministic fraud controls, human approval, and signed release workflows.
Actionproxy
Open-source approval gateway for AI agent tool calls: policy, human approval, one-time execution grants, and audit evidence.
Spectra Browser MCP
SpectraBrowser MCP: World-Class Autonomous Cognitive Browser Automation, Playwright Web Agent & Full-Spectrum Network QA Suite for AI Agents (Open WebUI, Claude, GPT-4o, DeepSeek)…