- 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.
Pairbrowse
Multiplayer browser sessions for developers and AI coding agents
Quickbooks MCP
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…
Quantcouncil
QuantCouncil: A-share multi-agent research and paper-trading platform (LangGraph, MCP, RAG, FastAPI, React)
Client Demo
Use the Pearl expert MCP server with the OpenAI Agent SDK
Apparitor
Vendor-neutral authorization for AI agents. Run the check inside the agent controls you already use (LlamaFirewall, NeMo Guardrails, FastMCP, A2A) and decide with the Policy-as-Co…
Multi Agent Orchestrator
Multi-agent orchestration built as production infrastructure: typed planning, a sandboxed tool registry, race-safe human-in-the-loop, deterministic replay, and a provably-terminat…
Vocion Core
Open source agent workforce platform. Next.js + Postgres + MCP server for AI agent teams with human-in-the-loop review, built in.
Bounded Agent Runtime
Security runtime for AI coding agents: bounded authority, exact-candidate evidence, separate review and human gates. Works with Codex, Claude and OpenCode.
DevdocAI
DevDocAI is a production-grade multi-agent AI system that automatically generates, maintains, and updates engineering documentation by deeply understanding you…DevDocAI is a produ…
Diplomat Gate
Runtime approval gates for AI agent tool calls. Intercept payments and emails before execution
Conn
Your agent works in your terminal. You keep the keyboard. A shared terminal with approvals, takeover and a record of what happened, for Claude Code, Codex, Cursor and GitHub Copil…
Jev Decisions
Jev Decisions Plugin for Hermes (and other AI Agents): tool risk reviews, human approval recommendations, evidence checks, and a local decision journal.
HelmRyth
A private operating system for autonomous work. Persistent operators that run on the CLIs you already own, crews that share a brief without sharing state, and a gate in front of e…
Maister
Self-hosted execution and governance for reproducible AI-powered software delivery over private code.
Excalidraw Pi Workspace
Excalidraw × Pi Agent 双向协作工作区：在官方 Excalidraw 无限画布上画结构化需求，经 MCP CLI + Review Gate 交给 AI 编码 Agent 执行，并将结果回写画布。 | Bidirectional Excalidraw ⇄ AI coding-agent workspace: sketch require…
Holco Finance Controls
Check financial AI outputs with an open protocol, 40 control requirements and 24 synthetic conformance cases. Local demo, no API key.
Helix SDK
Client SDKs for the Agent Execution Protocol (AEP), the wire protocol behind Helix
Kiri Gate
A gate in front of your AI agent's tools: acts on what can be undone, asks about what can't.
Hitl Support Agent
Production-grade Human-in-the-Loop customer support agent — LangGraph + real Gmail + real Slack + 3 capability-isolated MCP servers + v3↔v4 multi-agent head-to-head eval. Honest a…
Flow Weaver
Durable workflows compiled into TypeScript you own. MCP server for AI-written workflows.
SsuAgent
자연어 요청을 MCP 도구로 라우팅하고 승인·스트리밍·대화 상태를 관리하는 에이전트 오케스트레이션 서비스
AI Agent Firewall
Local-first security firewall for autonomous AI coding agents — intercepts, risk-scores, and human-approves every tool call (Claude Code / Codex / Cursor / Cline). Apache-2.0.
Nexora Sage
Local-first architecture context and evidence-backed analysis for React/TypeScript repositories and AI coding agents, with MCP tools.
Caliber Suite
Open-source MLflow plugin for AI agents and agentic workflows: prompts, tools, skills, MCP servers, RAG knowledge bases, evaluation, deployment, observability, and Aria copilot.
Clew
Lineage-based impact analysis and remediation for workflow runs. What a bad input or an incident report reached, what to re-run, delete or disclose, sealed as evidence an auditor…
Gatekeeper
Human-approved bridge between AI agents and your database through Beekeeper Studio.
Signal AI Agent Platform
Signal-native AI agent platform for realtime customer support & conversational commerce — multimodal messaging, LangGraph, RAG, MCP, Copilot, Qdrant, FastAPI & React.
Bigspy AI Connect Release
Public Windows downloads and product guide for BIGSPY AI Connect: a local-first AI workspace with project tasks, independent Cute Boss review, model connections and Resource Guard…
Penelope
Agent personnel autonome en Rust, tournant sans écran sur un Mac. Telegram ou SSH, mémoire en Markdown, serveurs MCP, workflows durables, approbation avant tout ce qui engage.
Headroom
More human oversight can make an AI agent less safe. Headroom is a human-in-the-loop firewall for coding agents that measures when to trust the human: oversight as resource alloca…
Agent Shield
为 LLM Agent 提供安全防护与审计框架，防御 MCP 投毒攻击，支持 HITL (Human-in-the-loop) 与审计调度。
Countersign
Your AI agent writes its own 'allow this?' dialog, so it can hide what it's really doing. Countersign draws the dialog itself, so you approve the real command, and every yes becom…
Apparitor
Vendor-neutral authorization for AI agents. Run the check inside the agent controls you already use (LlamaFirewall, NeMo Guardrails, FastMCP, A2A) and decide with the Policy-as-Co…
Mill
Guardrailed agentic workflows, on your desktop — agents and humans compose automations; a guardrail previews and gates every action before it happens. Single-binary Go + React (Wa…
Triage
Reads our meetings, Slack, GitHub, email and docs. Finds work that needs doing, and updates the task board. Pauses for a human when needed, and checks the live board first. Offlin…
Waypoint
LangGraph multi-agent trip planning system with parallel tool fan-out, Postgres checkpointing, and chat-based human review loop.
Enterprise Agent Lab
Reference implementation of controlled MCP agent workflows with independent human approval, LangGraph/native Python orchestration, and auditable writes.
Deep Coding Agent
A repo-scoped AI coding agent with in-editor diff approvals, built on LangChain deepagents + CopilotKit/AG-UI, Monaco, and MongoDB.
Across Orchestrator
Durable execution, quality gates, and evidence for supervised agent workflows.
DeepPairing
Review what Claude Code is about to change on a rich visual surface — inline comments, evidence, and a gate that remembers the approaches you rejected.
Bazz.agent
⚡ BAZZ.AGENT — Your Binance AI co-pilot: an Agent OS with MCP, Agentic Wallet, x402 & 19 skills. It acts on live markets — but every order waits for your nod.
Clawroom
Git for agent work. Everyone brings their own AI agent, every agent gets a Linux computer of its own, every tool call lands in a shared log like a commit, and nothing irreversible…
Binggupack
AI와 일하며 쌓이는 내 판단·실수·취향·규칙을, 자동 저장 없이 내가 승인한 것만 내 PC 장부에 남기고 다음 작업 전에 다시 꺼내주는 로컬 우선 개인 기억 엔진.
Eu AI Act Classifier
Deterministic EU AI Act classifier with source-backed review rows, obligation links, dossier artifacts, and blocked external actions.
Starlight
自托管的开源多模型 AI 智能体应用:ReAct 循环 + 计划执行 + 长期记忆 + 上下文压缩 + 子代理 + 人工审批 + MCP 扩展 + 流式思考 + Trace 回放 + 内置评估框架(25 任务 100% 通过)。14 个内置工具,五层安全防护,Flask + SQLite 轻量架构,双击即可部署,数据完全私有。
Nestor
Has a human checked this? Seal/serve/audit over verified-match memory — ledger, MCP, and CLI.
Qi
Qi (栖) is a local-first, event-driven Agent Runtime for people and Agents to share an observable, recoverable world—with durable goals, memory, bounded autonomy, and evidence-back…
Kontrol Freek MCP
AI assumption firewall for MCP agents — intercepts risky decisions, checks past decisions, detects contradictions, and gates human approval via Telegram or Slack.
Yuanzhu
Meta-Forge Workshop: turn recurring work into governed AI workflow assets. MCP server + Claude Code plugin + dsh plugin — staged writes, evals-gated forging, inference engine. 元铸工…
Skillfence
Runtime behavioral security for Agentic Skills — deterministic policy engine, human-in-the-loop gate, full OWASP Agentic Skills Top 10 (AST01–AST10) coverage. Not another SKILL.md…